© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77473
    Prev
    Next
    INDEX
    Explanations

    by or with local staff

    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_31_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
    Coroutine
    0.39
    INFO
    0.37
    Corruption
    0.36
     раду
    0.36
    Descriptions
    0.36
    Consumption
    0.36
     diantaranya
    0.35
    ڼ
    0.35
    Seeing
    0.35
    LOGO
    0.35
    POSITIVE LOGITS
     personnel
    0.44
     host
    0.40
     Kell
    0.40
     होस्ट
    0.40
     staff
    0.40
     Kanton
    0.40
     biographer
    0.39
    yst
    0.38
     Mitarbeiter
    0.38
    igment
    0.38
    Activations Density 0.001%

    No Known Activations