© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231884
    Prev
    Next
    INDEX
    Explanations

    reactive response

    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_6_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
     was
    0.81
     is
    0.70
    на
    0.64
    ה
    0.64
    1
    0.63
     to
    0.62
    Č
    0.61
    ه
    0.58
     Seit
    0.58
    É
    0.58
    POSITIVE LOGITS
     entornos
    0.59
    aparikkh
    0.58
    amental
    0.57
     иннова
    0.55
    iamo
    0.55
     ဒ
    0.55
    ς
    0.55
     actuation
    0.54
     capacitances
    0.54
     carcasses
    0.53
    Activations Density 0.000%

    No Known Activations