© 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. 236803
    Prev
    Next
    INDEX
    Explanations

    list of items; data; posts; tasks

    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
    섣
    0.40
     automático
    0.38
    DomainMask
    0.38
     tellement
    0.36
     साम्रा
    0.36
     paradox
    0.35
    indsight
    0.35
    侷
    0.35
    鉴定
    0.34
    ']))->
    0.34
    POSITIVE LOGITS
    ນ
    0.46
     ged
    0.42
     SDN
    0.41
     особо
    0.39
     Ged
    0.39
     ઘર
    0.39
     GED
    0.37
     berupa
    0.36
     hasil
    0.36
    leit
    0.36
    Activations Density 0.000%

    No Known Activations