© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7526
    Prev
    Next
    INDEX
    Explanations

    text related to evaluations with correct and incorrect responses

    oai_token-act-pair · gemini-2.0-flash

    questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     permanent
    -0.51
     См
    -0.48
     original
    -0.46
    subset
    -0.46
     Permanent
    -0.45
    جستارهای
    -0.45
    țial
    -0.45
    asında
    -0.45
     سكانية
    -0.45
     inéd
    -0.44
    POSITIVE LOGITS
    ilige
    0.52
    ecks
    0.52
    RenderAtEndOf
    0.51
    brale
    0.51
    viale
    0.50
    orative
    0.49
     magnético
    0.48
     visuelle
    0.48
    ONAUT
    0.47
    ATIVE
    0.47
    Activations Density 1.026%

    No Known Activations