© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    sentences that express opinions or thoughts, with a focus on beliefs and judgments.

    oai_token-act-pair · gemini-2.0-flash

    terms related to narratives or stories

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

    Unusual or foreign words

    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
    GroupLayout
    -0.43
     Column
    -0.42
     column
    -0.42
     কর
    -0.40
    ValueGeneration
    -0.39
    layan
    -0.38
     is
    -0.37
    сихо
    -0.37
    емость
    -0.36
    циали
    -0.36
    POSITIVE LOGITS
     kasarigan
    0.81
    ⓧ
    0.81
    Tikang
    0.74
    findpost
    0.70
    hdashline
    0.70
     Vikipedi
    0.69
     setTotal
    0.68
    GOTREF
    0.66
    Посилання
    0.65
     incomplete
    0.65
    Activations Density 3.443%

    No Known Activations