© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145996
    Prev
    Next
    INDEX
    Explanations

    Por

    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_59_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
     than
    0.48
    민
    0.42
     é
    0.41
     parallels
    0.40
    than
    0.38
     suspended
    0.38
     CARL
    0.38
     expected
    0.37
    Carl
    0.37
    가지
    0.37
    POSITIVE LOGITS
    Strafpunkte
    0.48
    (''
    0.44
    vamente
    0.39
    ァ
    0.39
     вода
    0.39
    FirstFit
    0.39
     য
    0.38
    Namara
    0.38
    ndrome
    0.38
    ]='
    0.38
    Activations Density 0.000%

    No Known Activations