© 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. 52922
    Prev
    Next
    INDEX
    Explanations

    code block prefixes

    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
    ]):
    0.39
     AudioClip
    0.37
     vš
    0.36
     сопро
    0.34
     प्रॉप
    0.34
     Indicates
    0.33
     accompan
    0.33
     сопровожда
    0.33
     Commentaires
    0.33
    Mannschaft
    0.32
    POSITIVE LOGITS
     anta
    0.34
    頜
    0.32
     spind
    0.32
     bebas
    0.32
    toml
    0.30
    imd
    0.30
     salva
    0.30
    कब
    0.30
    ভব
    0.29
    次第
    0.29
    Activations Density 0.007%

    No Known Activations