© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 205369
    Prev
    Next
    INDEX
    Explanations

    unwrapping/unwinding

    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
     wind
    1.33
     Wind
    1.23
     WIND
    1.16
    风
    1.13
    風
    1.13
    Wind
    1.13
    wind
    1.11
     winds
    1.05
     ветер
    0.91
     w
    0.90
    POSITIVE LOGITS
    adic
    0.40
    唕
    0.39
    sliding
    0.39
    Ec
    0.38
    hitting
    0.37
    ticker
    0.37
    يكم
    0.37
    τον
    0.35
    fullName
    0.35
     Ec
    0.35
    Activations Density 0.000%

    No Known Activations