© 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. 14842
    Prev
    Next
    INDEX
    Explanations

    the letter "W" in author names

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'W'

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

    W

    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
     derived
    -0.48
     No
    -0.46
     skins
    -0.45
     skin
    -0.45
     small
    -0.44
    癬
    -0.44
     there
    -0.43
    OrNil
    -0.42
     surface
    -0.42
     Herr
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.98
    CloseOperation
    0.75
    ponses
    0.75
    endphp
    0.69
     enfance
    0.67
    ImageContext
    0.67
    ]")]
    0.66
     ControllerBase
    0.65
     kasarigan
    0.63
     artikkelen
    0.63
    Activations Density 0.263%

    No Known Activations