© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200163
    Prev
    Next
    INDEX
    Explanations

    names and careers

    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_50_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
     чув
    0.40
    쌈
    0.38
     rosem
    0.37
     noy
    0.37
    ᱔
    0.36
    lexeme
    0.36
     resorting
    0.36
     রাস
    0.36
    iguez
    0.35
     ros
    0.35
    POSITIVE LOGITS
     HP
    0.42
    玤
    0.42
    HP
    0.41
    fted
    0.38
     BIL
    0.38
    defeated
    0.36
    емой
    0.36
    Expires
    0.36
     Ery
    0.36
    粖
    0.35
    Activations Density 0.000%

    No Known Activations