© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63361
    Prev
    Next
    INDEX
    Explanations

    headings or listening

    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_46_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
     Bata
    0.42
    ǫ
    0.41
     pepe
    0.41
     writing
    0.40
     escrit
    0.39
    केट
    0.38
     objetivo
    0.38
     DU
    0.38
    ಢ
    0.37
     efecto
    0.37
    POSITIVE LOGITS
     heading
    0.47
     Heading
    0.47
    Listen
    0.46
     nghe
    0.44
    Heading
    0.43
     леген
    0.42
     Listener
    0.41
    heading
    0.40
     listen
    0.40
    听
    0.40
    Activations Density 0.000%

    No Known Activations