© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12908
    Prev
    Next
    INDEX
    Explanations

    instances where legal or financial information is being given, sometimes implying zeal or newness

    oai_token-act-pair · gemini-2.0-flash

    legal/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     cual
    -0.46
     }}"></
    -0.43
    TypeOf
    -0.42
     He
    -0.41
     nouvelle
    -0.40
    чер
    -0.39
    Источники
    -0.38
    ate
    -0.38
     keting
    -0.38
     esper
    -0.38
    POSITIVE LOGITS
    舺
    0.77
     BoxFit
    0.77
     муніципалі
    0.76
     Efq
    0.74
     defaultstate
    0.74
    UnsafeEnabled
    0.73
     pleaſure
    0.73
     kaarangay
    0.73
    featureID
    0.71
     vectorstock
    0.71
    Activations Density 0.651%

    No Known Activations