© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201701
    Prev
    Next
    INDEX
    Explanations

    critical analysis

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    licted
    0.43
    ned
    0.41
    NED
    0.40
     %``
    0.38
     полный
    0.37
    Dis
    0.36
    sworth
    0.36
    Jab
    0.36
    genden
    0.35
     anuncia
    0.35
    POSITIVE LOGITS
     mechanics
    0.40
    탭
    0.40
    ឹ
    0.38
    机器
    0.37
     एडमिशन
    0.37
     విజ
    0.37
    教学
    0.36
    ത്യാ
    0.36
     ratio
    0.36
    面的
    0.36
    Activations Density 0.011%

    No Known Activations