© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175347
    Prev
    Next
    INDEX
    Explanations

    receptor compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    result
    0.46
    params
    0.45
    ?',
    0.43
    where
    0.42
    ्यांना
    0.42
    idemargin
    0.42
    𒍪
    0.41
    selectors
    0.41
     Precio
    0.41
    }",
    0.41
    POSITIVE LOGITS
     держави
    0.44
     basa
    0.43
     للك
    0.43
     بين
    0.43
     forcible
    0.42
    மன்
    0.41
     proportionality
    0.41
    出门
    0.40
     κε
    0.40
     sage
    0.40
    Activations Density 0.000%

    No Known Activations