© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198961
    Prev
    Next
    INDEX
    Explanations

    has

    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_46_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
     tacked
    0.41
    分配
    0.38
    संग
    0.38
    育て
    0.38
     RAI
    0.37
    цене
    0.37
     dovet
    0.37
    뉜
    0.37
    Meeting
    0.36
    ('\
    0.36
    POSITIVE LOGITS
     ايه
    0.36
    jersey
    0.36
     NO
    0.36
    slip
    0.36
    }?
    0.35
     جائے
    0.35
    oyer
    0.35
    grip
    0.35
     no
    0.35
     głównie
    0.35
    Activations Density 0.001%

    No Known Activations