© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234150
    Prev
    Next
    INDEX
    Explanations

    st ool

    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_32_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
     presence
    0.41
     موز
    0.38
    Три
    0.37
    鸠
    0.36
     Presence
    0.35
     too
    0.35
    এড
    0.34
    Av
    0.34
    Transc
    0.34
    <h3>
    0.33
    POSITIVE LOGITS
    ulla
    0.43
    өх
    0.40
    वळ
    0.39
    havior
    0.38
     물론
    0.36
    собен
    0.36
     Callahan
    0.36
    棸
    0.35
    illen
    0.35
    ufen
    0.34
    Activations Density 0.008%

    No Known Activations