© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205287
    Prev
    Next
    INDEX
    Explanations

    concurring with agreement

    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_6_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
    1.16
    u
    1.14
    )
    1.09
    ।
    1.02
    s
    1.01
    k
    0.93
     meny
    0.90
    dan
    0.85
    dos
    0.85
    daki
    0.84
    POSITIVE LOGITS
    вається
    1.01
    𝕦
    1.01
     Vì
    0.98
    𝚊
    0.93
    ρα
    0.93
    رفة
    0.93
    intérêt
    0.93
    revoke
    0.90
    ینہ
    0.90
     وړاندوینې
    0.89
    Activations Density 0.000%

    No Known Activations