© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194649
    Prev
    Next
    INDEX
    Explanations

    generating reports

    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_9_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
    -
    0.55
    로
    0.53
    AD
    0.49
    ca
    0.48
    ash
    0.47
    ılar
    0.47
    OT
    0.47
    кі
    0.45
    AY
    0.45
    riving
    0.44
    POSITIVE LOGITS
    ?
    0.64
    тся
    0.47
     informe
    0.46
     úd
    0.45
     attribu
    0.44
     přip
    0.44
     archiv
    0.44
     نيك
    0.43
     sacr
    0.42
     observé
    0.41
    Activations Density 0.009%

    No Known Activations