© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204497
    Prev
    Next
    INDEX
    Explanations

    search for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     Utilization
    0.42
     Handicap
    0.41
     Día
    0.40
    機會
    0.40
     utilization
    0.38
     Utilizing
    0.38
    magenta
    0.37
    驕
    0.36
    ⸩
    0.36
    ֣
    0.36
    POSITIVE LOGITS
    Glu
    0.40
    schr
    0.37
     grosse
    0.36
    ̆
    0.36
     serial
    0.35
    ğimiz
    0.35
    emis
    0.35
    ກ
    0.35
     seyd
    0.35
     jeu
    0.35
    Activations Density 0.001%

    No Known Activations