© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108041
    Prev
    Next
    INDEX
    Explanations

    hemen `ona`

    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
    ال
    1.43
    न
    1.43
     that
    1.36
     que
    1.29
    на
    1.24
    ন
    1.20
    2
    1.19
    ਰ
    1.19
     you
    1.14
    ie
    1.10
    POSITIVE LOGITS
    tia
    0.89
    ↵
    0.89
    t
    0.84
     Streptococcus
    0.84
    OnFileChange
    0.83
    లి
    0.83
    дя
    0.83
     линия
    0.82
     Lactobacillus
    0.82
     Src
    0.80
    Activations Density 0.001%

    No Known Activations