© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197414
    Prev
    Next
    INDEX
    Explanations

    rules and boundaries

    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_27_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
    便利
    0.34
    ਸ
    0.33
     Проци
    0.33
     मजेदार
    0.32
    withtag
    0.31
    ਕ
    0.31
    𒋾
    0.31
     гос
    0.30
    Economics
    0.30
    栥
    0.30
    POSITIVE LOGITS
     coax
    0.29
     force
    0.27
     coisa
    0.27
    ارع
    0.27
     arr
    0.27
     peso
    0.26
     limbs
    0.26
     బె
    0.26
     balloons
    0.26
     asked
    0.26
    Activations Density 0.002%

    No Known Activations