© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49005
    Prev
    Next
    INDEX
    Explanations

    system interactions

    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_55_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
    立
    0.42
    rectionType
    0.37
     හර
    0.37
    ไว้
    0.36
    者を
    0.36
    ตา
    0.36
    гаа
    0.36
     součást
    0.36
    readystate
    0.35
    xhtml
    0.35
    POSITIVE LOGITS
    審
    0.38
    वेयर
    0.37
    licks
    0.36
    ajit
    0.36
    AW
    0.35
     surround
    0.35
    OUR
    0.35
     PHILLIPS
    0.35
    មើ
    0.34
    AU
    0.34
    Activations Density 0.000%

    No Known Activations