© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91340
    Prev
    Next
    INDEX
    Explanations

    self, plan, fortune

    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
    sleep
    0.45
    oct
    0.39
    癖
    0.39
    waveform
    0.39
    村
    0.38
    睡
    0.38
     Sleep
    0.37
    village
    0.37
    ushan
    0.37
    überküloz
    0.37
    POSITIVE LOGITS
    化
    0.47
     化
    0.44
    فكير
    0.41
     hóa
    0.40
    علان
    0.40
    ifiant
    0.39
    Carolina
    0.39
    維
    0.39
     proclaiming
    0.38
    ிழமை
    0.38
    Activations Density 0.003%

    No Known Activations