© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203004
    Prev
    Next
    INDEX
    Explanations

    print keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     responded
    0.43
     Mu
    0.42
     retaliation
    0.40
     liter
    0.39
    玦
    0.39
     Ah
    0.38
     reprinted
    0.38
     Loops
    0.38
     کردی
    0.38
    쓴
    0.38
    POSITIVE LOGITS
     verbally
    0.54
    StudentNo
    0.42
     orally
    0.40
    (__('
    0.40
     للنساء
    0.38
     Oral
    0.38
    超過
    0.38
    getSeconds
    0.38
     Verbal
    0.38
    lebihan
    0.38
    Activations Density 0.003%

    No Known Activations