© 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. 121842
    Prev
    Next
    INDEX
    Explanations

    places and proper nouns

    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
    érature
    0.39
    parsers
    0.37
     expt
    0.36
    𝒋
    0.36
     Frankfurt
    0.36
    ího
    0.36
    стройства
    0.35
     Nicholas
    0.35
     frank
    0.35
    composable
    0.35
    POSITIVE LOGITS
     Twin
    0.48
     Motel
    0.46
     Panther
    0.44
     motel
    0.43
     Echo
    0.41
    Twin
    0.41
    )}}\
    0.40
     Jet
    0.39
    Chromatic
    0.39
     Hi
    0.39
    Activations Density 0.010%

    No Known Activations