© 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. 12203
    Prev
    Next
    INDEX
    Explanations

    code and associated characters

    oai_token-act-pair · gemini-2.0-flash

    number seven

    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
     Lili
    -0.71
    Leslie
    -0.64
     Leslie
    -0.64
    Lili
    -0.64
     Mung
    -0.64
    unger
    -0.63
    קישורים
    -0.60
     Kingfisher
    -0.59
     psoriasis
    -0.59
     SJ
    -0.59
    POSITIVE LOGITS
     vii
    0.79
    7
    0.79
     seventh
    0.73
     VII
    0.71
    VII
    0.67
    seventh
    0.66
     Levine
    0.65
     seventeenth
    0.64
    vii
    0.64
    Seventh
    0.64
    Activations Density 11.212%

    No Known Activations