© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167610
    Prev
    Next
    INDEX
    Explanations

    component update

    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_34_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
    fread
    0.37
     Teor
    0.35
     деле
    0.34
    вым
    0.33
    してた
    0.33
    近い
    0.32
    ủ
    0.32
    füh
    0.32
     dec
    0.32
    que
    0.32
    POSITIVE LOGITS
     เท่า
    0.39
    Isometric
    0.37
     peringkat
    0.36
     پیروی
    0.36
     Kut
    0.35
     면
    0.35
     രീതി
    0.35
     componentDid
    0.35
     isometric
    0.34
    ViewHolder
    0.34
    Activations Density 0.000%

    No Known Activations