© 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
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 248689
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ινό
    0.40
    Ꮠ
    0.38
     गिवन
    0.37
     Hum
    0.36
    Chel
    0.36
    Muse
    0.36
    어를
    0.36
     انگلیسی
    0.36
     તમને
    0.36
    сию
    0.36
    POSITIVE LOGITS
     firm
    0.77
    風
    0.73
    wind
    0.72
    风
    0.72
     winds
    0.71
     wind
    0.70
     firms
    0.68
     Firm
    0.68
     firma
    0.68
     Firms
    0.68
    Activations Density 0.001%

    No Known Activations