© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109317
    Prev
    Next
    INDEX
    Explanations

    Rajah

    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_2_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
     îl
    1.08
    r
    1.03
     sfâr
    0.99
     کی
    0.98
    기
    0.98
    ஜித்
    0.97
     coupé
    0.97
     pasukan
    0.96
    ών
    0.95
     سایت
    0.95
    POSITIVE LOGITS
    ja
    1.42
     ja
    1.20
    ע
    1.16
     Ja
    1.13
    Ja
    1.12
    ية
    1.05
    要
    1.05
    ır
    1.00
    ко
    0.98
    un
    0.96
    Activations Density 0.000%

    No Known Activations