© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194631
    Prev
    Next
    INDEX
    Explanations

    stakeholder engagement & participation

    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_15_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
    에서
    0.22
    _
    0.19
    -
    0.19
    소
    0.18
    CL
    0.18
     primary
    0.18
    (/\
    0.18
    CV
    0.18
    7
    0.18
    ERS
    0.17
    POSITIVE LOGITS
    pped
    0.20
    fassung
    0.19
    鈁
    0.19
    рования
    0.19
    вание
    0.19
    饭
    0.19
    soir
    0.18
    ⚜
    0.18
    brar
    0.18
     Smoothing
    0.18
    Activations Density 0.004%

    No Known Activations