© 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. 121473
    Prev
    Next
    INDEX
    Explanations

    trained by Google DeepMind

    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
     primarily
    0.39
     अदिति
    0.38
     selectively
    0.35
    ឌ
    0.35
     discriminatory
    0.35
    합
    0.35
     die
    0.34
    탄소년단
    0.34
    isfile
    0.34
    ldef
    0.34
    POSITIVE LOGITS
    supervisor
    0.38
    लट्
    0.38
     ऋ
    0.38
     ಹೇಳಿದರು
    0.37
     Supervisors
    0.36
     supervisor
    0.36
    他们的
    0.36
    क्ल
    0.36
    zinc
    0.35
     करतात
    0.35
    Activations Density 0.011%

    No Known Activations