© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102465
    Prev
    Next
    INDEX
    Explanations

    Bay Beach

    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_14_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
    D
    0.61
    C
    0.56
    M
    0.55
    crypto
    0.47
    cardia
    0.47
     Setup
    0.46
    د
    0.46
    М
    0.46
    ه
    0.45
     booklet
    0.45
    POSITIVE LOGITS
    na
    0.53
     seren
    0.53
    㳖
    0.52
     ouvrir
    0.51
    깥
    0.51
     horrend
    0.51
     vzduchu
    0.50
     guitarra
    0.49
     integrada
    0.49
     origine
    0.49
    Activations Density 0.000%

    No Known Activations