© 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. 251552
    Prev
    Next
    INDEX
    Explanations

    hook

    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
    Rooms
    0.42
    Expressions
    0.42
     appended
    0.40
    Wash
    0.40
    /
    0.40
    Room
    0.39
     shared
    0.39
     yards
    0.38
    rooms
    0.38
     Rooms
    0.38
    POSITIVE LOGITS
     hook
    1.33
     Hook
    1.25
    Hook
    1.16
    hook
    1.13
     hooks
    1.13
    HOOK
    1.13
     hooking
    1.13
     hooked
    1.12
    钩
    1.12
     Hooks
    1.11
    Activations Density 0.000%

    No Known Activations