© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199612
    Prev
    Next
    INDEX
    Explanations

    string formatting or quotes

    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_27_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
    roly
    0.32
     கட்டமை
    0.32
    ोबर
    0.31
    startX
    0.30
    スペ
    0.30
     একখানি
    0.29
    Ờ
    0.29
    简洁
    0.29
    Maxima
    0.28
    独立的
    0.28
    POSITIVE LOGITS
     nemoc
    0.39
     unless
    0.33
    any
    0.32
     कारक
    0.31
     każ
    0.30
     Abandon
    0.30
    疫情
    0.29
    の影響
    0.29
     szpital
    0.28
    .**
    0.28
    Activations Density 0.014%

    No Known Activations