© 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. 76419
    Prev
    Next
    INDEX
    Explanations

    resource requests

    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
    ènement
    0.32
     linearity
    0.31
     voul
    0.29
    arbeiter
    0.29
    等级
    0.29
    사업
    0.28
     ajout
    0.28
    ｲ
    0.28
     volumen
    0.28
     INDUSTRY
    0.28
    POSITIVE LOGITS
    クロ
    0.31
     Te
    0.30
     consigo
    0.26
     Goff
    0.26
     قوت
    0.26
     クロ
    0.26
    ләү
    0.26
     油
    0.26
    の中から
    0.25
     Jer
    0.25
    Activations Density 0.000%

    No Known Activations