© 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. 232706
    Prev
    Next
    INDEX
    Explanations

    shaman

    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
    mist
    0.43
    Mist
    0.40
    缄
    0.39
     Mist
    0.39
    蟲
    0.38
    onica
    0.38
    cort
    0.38
    psons
    0.37
    seas
    0.37
     Soldier
    0.36
    POSITIVE LOGITS
    拦
    0.40
    Panning
    0.39
     타이
    0.39
     rãi
    0.39
     সম্প্র
    0.38
     Satisf
    0.38
     優
    0.38
    ManagerPortal
    0.38
     interracial
    0.38
     blessing
    0.37
    Activations Density 0.000%

    No Known Activations