© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150571
    Prev
    Next
    INDEX
    Explanations

    place names

    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_60_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
    し
    1.21
     し
    0.75
     sh
    0.70
    sh
    0.63
     Sh
    0.61
    をし
    0.56
    にし
    0.53
     shunt
    0.52
     ش
    0.49
     శ
    0.46
    POSITIVE LOGITS
    こと
    0.67
    ことです
    0.52
    ことで
    0.51
     こと
    0.43
    事
    0.43
    Provence
    0.41
    Simulator
    0.40
    Defender
    0.40
    Sunrise
    0.39
    Nuevo
    0.39
    Activations Density 0.000%

    No Known Activations