© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63326
    Prev
    Next
    INDEX
    Explanations

    legal and chemical contexts

    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_59_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
    itos
    0.38
    table
    0.36
    MainActivity
    0.35
    iv
    0.35
    㝌
    0.35
    itsch
    0.35
     reallocation
    0.35
     flatness
    0.35
    textView
    0.34
     bedside
    0.34
    POSITIVE LOGITS
    T
    0.98
    R
    0.93
    E
    0.84
    RU
    0.77
    O
    0.72
    TEN
    0.71
    RIM
    0.71
    ECTION
    0.71
    Rn
    0.69
    ELL
    0.67
    Activations Density 0.000%

    No Known Activations