© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 857
    Prev
    Next
    INDEX
    Explanations

    exploring rabbit holes

    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_44_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
    (',
    0.40
    оне
    0.39
     Aurang
    0.39
     f
    0.38
    ських
    0.37
     complains
    0.37
     collider
    0.37
     Wirkung
    0.37
    豈
    0.37
     дели
    0.36
    POSITIVE LOGITS
     Smart
    0.39
    而言
    0.39
    初代
    0.37
    TLV
    0.37
    eber
    0.37
    Translator
    0.36
     SAR
    0.35
    --
    0.35
    ieß
    0.35
     axiom
    0.35
    Activations Density 0.044%

    No Known Activations