© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209060
    Prev
    Next
    INDEX
    Explanations

    output fields and configuration

    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_25_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
     immobilization
    0.38
    Geocoder
    0.38
    ierrez
    0.37
    Upgradeable
    0.37
    Battery
    0.36
    गानिस्तान
    0.36
    Monster
    0.36
    /****
    0.35
     taller
    0.34
    Assassin
    0.34
    POSITIVE LOGITS
     nuo
    0.38
     มิถุนายน
    0.37
     Antonio
    0.36
    哭了
    0.35
     Why
    0.35
     선수
    0.35
     범위
    0.35
    vish
    0.35
    fi
    0.35
     больших
    0.34
    Activations Density 0.001%

    No Known Activations