© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169006
    Prev
    Next
    INDEX
    Explanations

    -

    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_56_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
     FUT
    0.32
     encouraging
    0.32
     critical
    0.31
     Sü
    0.31
    тем
    0.30
    辇
    0.30
     WE
    0.30
     GLUT
    0.29
     BIO
    0.29
     eternal
    0.29
    POSITIVE LOGITS
    State
    0.33
     };
    0.32
    Much
    0.31
    icoes
    0.31
     ډول
    0.30
    itatively
    0.29
    Constit
    0.29
    Encom
    0.28
    ina
    0.28
     p
    0.28
    Activations Density 0.002%

    No Known Activations