© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    words that describe improvement of a product or service

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     –,
    -0.91
     ─
    -0.88
     —
    -0.88
     --
    -0.87
    ,—
    -0.86
    érables
    -0.83
     −
    -0.82
     --;
    -0.81
    /−
    -0.79
     –
    -0.79
    POSITIVE LOGITS
     виправивши
    0.57
     courants
    0.49
     ennemis
    0.41
     prêtres
    0.41
     religieuses
    0.41
     pouvoirs
    0.39
    Enllaces
    0.39
     vícti
    0.39
     fidé
    0.38
     preuves
    0.37
    Activations Density 13.132%

    No Known Activations