© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3244
    Prev
    Next
    INDEX
    Explanations

    scientific or technical words ending in "ans", "can", or "arin" or other words related to biomass.

    oai_token-act-pair · gemini-2.0-flash

    scientific and biological studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    tagHelperRunner
    -0.74
    migrationBuilder
    -0.70
    providedIn
    -0.68
     متعلقه
    -0.61
     مشين
    -0.60
    ribadian
    -0.58
     JpaRepository
    -0.57
    :+:
    -0.56
    getDoctrine
    -0.56
     useStyles
    -0.55
    POSITIVE LOGITS
    MigrationBuilder
    0.59
    VIAF
    0.56
     Frist
    0.46
    Personendaten
    0.45
     locator
    0.45
     nevoie
    0.44
    ocha
    0.44
     Kurt
    0.44
     Hum
    0.43
    ìm
    0.43
    Activations Density 2.052%

    No Known Activations