© 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. 231836
    Prev
    Next
    INDEX
    Explanations

    anyone asking a question

    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
    ل
    1.50
    O
    1.22
    ر
    1.19
     by
    1.18
    ל
    1.16
    জ
    1.11
    О
    1.11
    ،
    1.07
    ר
    1.05
    src
    1.03
    POSITIVE LOGITS
     läk
    0.89
    し
    0.83
    ose
    0.79
    的其他
    0.78
    с
    0.77
    ledge
    0.73
    の見
    0.72
     soldering
    0.71
     obtuse
    0.71
     경험
    0.71
    Activations Density 0.001%

    No Known Activations