© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8843
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is giving their opinion about something that they either recently read, watched, or experienced

    oai_token-act-pair · gemini-2.0-flash

    generic positive reviews

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.72
    Jeografia
    -0.65
    here
    -0.63
    adaptiveStyles
    -0.59
     here
    -0.57
     Wikimedijinoj
    -0.57
     članak
    -0.56
    WriteTagHelper
    -0.50
     EconPapers
    -0.50
     ride
    -0.50
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.64
    }))
    0.58
    Portale
    0.57
    (;;)
    0.55
    favorited
    0.54
    outheast
    0.53
    RenderAtEndOf
    0.52
    Highly
    0.52
    %")
    0.52
    assium
    0.51
    Activations Density 1.384%

    No Known Activations