© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177023
    Prev
    Next
    INDEX
    Explanations

    breakdown of key aspects

    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_24_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
     скульп
    0.33
     đầy
    0.32
     popolazione
    0.31
    護
    0.31
    ியின்
    0.31
    㸮
    0.31
     Н
    0.31
     propiedad
    0.31
     sekar
    0.30
     bloque
    0.30
    POSITIVE LOGITS
    Arrow
    0.32
    (~
    0.29
    Use
    0.29
    Taxi
    0.29
    Accessories
    0.28
    akers
    0.28
    (__
    0.28
    Around
    0.28
    </b>
    0.27
    arding
    0.27
    Activations Density 0.003%

    No Known Activations