© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251802
    Prev
    Next
    INDEX
    Explanations

    French

    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_56_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
    impurity
    0.40
    Intersect
    0.39
    箕
    0.38
    elos
    0.38
     знамена
    0.38
    سٹر
    0.37
    akul
    0.36
    cohort
    0.36
    LuaPush
    0.36
     intersect
    0.35
    POSITIVE LOGITS
    French
    0.44
     Tou
    0.44
     French
    0.42
    Tou
    0.41
     ante
    0.40
    煎
    0.40
    french
    0.39
     Silverman
    0.39
     Neigh
    0.38
     contra
    0.38
    Activations Density 0.004%

    No Known Activations