© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3659
    Prev
    Next
    INDEX
    Explanations

    timestamp start 0:00

    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_39_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
     hakim
    0.40
    彙
    0.39
     ger
    0.38
    Pen
    0.38
     shorten
    0.36
    ష్టం
    0.36
    LIN
    0.36
    isco
    0.35
     rew
    0.34
     steeper
    0.34
    POSITIVE LOGITS
    మవు
    0.40
     Synd
    0.39
    ፫
    0.38
    urii
    0.38
    udem
    0.38
    уса
    0.38
     rotated
    0.37
     pédicule
    0.36
     ಸಿನಿಮಾ
    0.36
     sillä
    0.35
    Activations Density 0.003%

    No Known Activations