© 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. 107718
    Prev
    Next
    INDEX
    Explanations

    compilation of

    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
    s
    1.46
    ی
    1.16
    ség
    1.05
    ς
    0.98
    ר
    0.91
     has
    0.89
    ের
    0.89
    szer
    0.80
    时
    0.79
     alumno
    0.79
    POSITIVE LOGITS
     it
    1.08
    ic
    0.99
    ل
    0.96
    os
    0.92
     ότι
    0.92
    ong
    0.88
    い
    0.88
    ある
    0.86
     that
    0.86
    いた
    0.85
    Activations Density 0.002%

    No Known Activations