© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167608
    Prev
    Next
    INDEX
    Explanations

    study methodology/description

    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_31_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
     perd
    0.41
     начали
    0.39
     utilizados
    0.39
    铍
    0.39
     dham
    0.38
    жал
    0.38
    धार
    0.36
    ়া
    0.36
     আসলে
    0.35
    适配
    0.35
    POSITIVE LOGITS
     mental
    0.44
    mental
    0.42
     undertaking
    0.42
     anaphyl
    0.40
    -%
    0.39
     controlling
    0.37
    keletal
    0.37
     improvements
    0.36
     objectivity
    0.36
     remittances
    0.36
    Activations Density 0.000%

    No Known Activations