© 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. 66680
    Prev
    Next
    INDEX
    Explanations

    month

    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
     renversement
    0.42
     అంతే
    0.37
    🔟
    0.37
     dimensionless
    0.37
     ნაკ
    0.37
     skal
    0.36
     needles
    0.36
    ᓇ
    0.36
     कामना
    0.35
    ружи
    0.35
    POSITIVE LOGITS
     keypad
    0.44
    情報の
    0.41
     तिथि
    0.40
     bát
    0.40
    date
    0.38
    HEY
    0.38
    Kennedy
    0.37
     الخم
    0.37
     date
    0.37
     Хан
    0.36
    Activations Density 0.002%

    No Known Activations