© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217952
    Prev
    Next
    INDEX
    Explanations

    rivers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     vos
    0.49
     Wo
    0.46
     Vog
    0.46
     Vos
    0.43
    vos
    0.43
    ške
    0.42
     coû
    0.42
    ̺
    0.41
     Doc
    0.41
     मै
    0.40
    POSITIVE LOGITS
     holog
    0.39
    检察
    0.39
     stimulating
    0.38
     Ust
    0.38
    ferd
    0.38
    டியில்
    0.37
    óri
    0.37
    sembly
    0.37
    atlan
    0.36
    inar
    0.36
    Activations Density 0.000%

    No Known Activations