© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212308
    Prev
    Next
    INDEX
    Explanations

    Structured request schema

    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_5_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
    u
    1.52
    al
    1.40
    have
    1.27
    Have
    1.25
    im
    1.16
    ről
    1.13
    er
    1.08
    ur
    1.06
    s
    1.03
    it
    1.02
    POSITIVE LOGITS
    1.40
    ري
    1.23
    ви
    1.21
    н
    1.07
    EN
    1.04
    ن
    1.02
    та
    1.01
    е
    1.01
    كل
    0.98
    ET
    0.96
    Activations Density 0.000%

    No Known Activations