© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36537
    Prev
    Next
    INDEX
    Explanations

    point should you

    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_11_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
    นัก
    0.58
    harmonic
    0.56
     Civic
    0.56
    นคร
    0.56
    的
    0.55
    impression
    0.54
    ́t
    0.52
    healthcare
    0.52
    as
    0.52
    রাই
    0.52
    POSITIVE LOGITS
    ك
    0.70
    r
    0.67
    야
    0.64
    )}/>
    0.63
    a
    0.63
    크
    0.62
    )
    0.61
     sencillo
    0.60
    ce
    0.57
     spots
    0.56
    Activations Density 0.002%

    No Known Activations