© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14629
    Prev
    Next
    INDEX
    Explanations

    communication alerts

    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_15_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
     પ્રથમ
    0.55
     ƙ
    0.52
     ይህ
    0.51
     buddhav
    0.50
    ार्टम
    0.49
     γεγον
    0.49
     thuyết
    0.49
     didactic
    0.48
     Ρ
    0.48
     χωρίς
    0.48
    POSITIVE LOGITS
    vered
    0.47
    bido
    0.46
     उर्
    0.46
    uze
    0.46
    õ
    0.46
    ધાર
    0.45
    )
    0.45
    iene
    0.44
    )$
    0.43
    aur
    0.43
    Activations Density 0.007%

    No Known Activations