© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24857
    Prev
    Next
    INDEX
    Explanations

    shortcuts

    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_10_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
    in
    0.76
    も
    0.66
    も含
    0.66
    infection
    0.64
    traumatic
    0.61
     सामना
    0.61
    edged
    0.59
    ᱒
    0.58
    venues
    0.57
    importance
    0.57
    POSITIVE LOGITS
     this
    0.59
    n
    0.55
    nse
    0.55
    าว
    0.50
    ッサ
    0.50
     null
    0.50
    ส์
    0.50
     monomial
    0.50
     הסי
    0.49
     Wasn
    0.49
    Activations Density 0.000%

    No Known Activations