© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154189
    Prev
    Next
    INDEX
    Explanations

    actions or operations

    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_60_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
     The
    0.55
    ↵
    0.53
     A
    0.52
     h
    0.43
    us
    0.41
     or
    0.41
    ismo
    0.41
     the
    0.40
    ↵↵↵↵
    0.39
     v
    0.38
    POSITIVE LOGITS
    From
    0.62
    All
    0.61
    Call
    0.57
    Clone
    0.55
    Build
    0.54
    Merge
    0.54
    Save
    0.54
    Resolve
    0.54
    Plan
    0.53
    Multi
    0.52
    Activations Density 0.000%

    No Known Activations