© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261613
    Prev
    Next
    INDEX
    Explanations

    content structure

    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_22_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
     그랬
    0.38
    बांग
    0.38
     hMut
    0.37
    咊
    0.37
    ꔰ
    0.37
    словия
    0.36
    姗
    0.36
     ಬಯ
    0.36
    其
    0.36
    ｰ
    0.36
    POSITIVE LOGITS
     opa
    0.43
     faint
    0.43
     potential
    0.41
     dominating
    0.39
     poured
    0.39
    ळा
    0.38
     well
    0.38
    idity
    0.38
     top
    0.38
     thrown
    0.38
    Activations Density 0.000%

    No Known Activations