© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35924
    Prev
    Next
    INDEX
    Explanations

    known information/facts

    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_11_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
    ע
    0.57
    ज्ञानिक
    0.57
    ರಿದ
    0.57
     prava
    0.57
    iteta
    0.57
    ം
    0.55
    டக
    0.55
    铡
    0.55
    ge
    0.54
    ர்
    0.54
    POSITIVE LOGITS
     يج
    0.65
    -
    0.62
    RESULT
    0.62
    Air
    0.60
    Massage
    0.60
    Л
    0.59
     Wasn
    0.57
    LayoutInflater
    0.57
    Zur
    0.56
    layout
    0.56
    Activations Density 0.007%

    No Known Activations