© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213916
    Prev
    Next
    INDEX
    Explanations

    Pros

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     CONS
    0.46
     Cons
    0.46
    ᱖
    0.39
    cons
    0.39
     рыб
    0.39
    ชี
    0.38
    旋转
    0.38
     কথোপ
    0.37
    Cons
    0.36
    ypi
    0.36
    POSITIVE LOGITS
    निज
    0.39
    aitre
    0.38
     bilir
    0.37
    льность
    0.36
    spraak
    0.36
    artment
    0.36
     NICE
    0.36
     $+
    0.36
    aligned
    0.35
     less
    0.35
    Activations Density 0.003%

    No Known Activations