© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    oai_token-act-pair · gemini-2.0-flash

    programming variable names or code elements

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

    Code snippets

    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
    ard
    -0.46
     Rock
    -0.44
     Katzen
    -0.44
     Bradley
    -0.43
     Drop
    -0.43
    ("")]
    -0.41
    zzer
    -0.41
     Stefani
    -0.40
     de
    -0.40
    <eos>
    -0.40
    POSITIVE LOGITS
    setVerticalGroup
    0.89
     Efq
    0.84
    Спасылкі
    0.81
    UrlResolution
    0.81
     againſt
    0.80
     raiſ
    0.79
    Hochspringen
    0.78
    RenderAtEndOf
    0.77
    aarrggbb
    0.77
    findpost
    0.77
    Activations Density 9.763%

    No Known Activations