© 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. 13967
    Prev
    Next
    INDEX
    Explanations

    license agreements and disclaimers

    oai_token-act-pair · gemini-2.0-flash

    without warranty

    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
    ViewFeatures
    -0.65
     poffible
    -0.63
     Pues
    -0.62
     wherefore
    -0.61
    OGND
    -0.59
     Roskov
    -0.59
     مُعرِّف
    -0.59
     MainAxisSize
    -0.59
     suivantes
    -0.58
     mitä
    -0.57
    POSITIVE LOGITS
     AGAIN
    0.52
     Film
    0.52
    MigrationBuilder
    0.50
     DOES
    0.49
     MUCH
    0.49
     ONCE
    0.49
     ALSO
    0.48
     REALLY
    0.48
     MANY
    0.48
     FINALLY
    0.48
    Activations Density 3.531%

    No Known Activations