© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126994
    Prev
    Next
    INDEX
    Explanations

    cultural artifacts, industries, icons, contributions

    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_3_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
    I
    0.79
    IC
    0.75
    ella
    0.74
    been
    0.74
    tet
    0.71
    pri
    0.70
    ler
    0.69
    AN
    0.69
    pat
    0.67
    an
    0.67
    POSITIVE LOGITS
    🔷
    0.67
    ות
    0.66
    த்தில்
    0.62
     stave
    0.61
    ியின்
    0.60
    டை
    0.60
     obstante
    0.60
    狄
    0.60
     FODC
    0.59
    ﻓ
    0.58
    Activations Density 0.004%

    No Known Activations