© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134045
    Prev
    Next
    INDEX
    Explanations

    place names

    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_37_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
     bef
    0.39
    阆
    0.39
    телями
    0.38
     Outreach
    0.38
    的反
    0.38
    ப்பா
    0.36
     lind
    0.36
     meeting
    0.36
     sulph
    0.35
     Chance
    0.35
    POSITIVE LOGITS
    attam
    0.42
    桟
    0.42
    Cleveland
    0.40
     individualism
    0.40
     Cleveland
    0.40
    流通
    0.39
     circula
    0.39
     фра
    0.38
    economy
    0.37
    羞
    0.37
    Activations Density 0.000%

    No Known Activations