© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104926
    Prev
    Next
    INDEX
    Explanations

    immerse yourself

    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_1_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
     to
    1.51
     I
    1.48
     for
    1.38
     with
    1.30
     at
    1.29
     you
    1.19
    .
    1.19
     be
    1.18
     It
    1.18
    ă
    1.13
    POSITIVE LOGITS
    ي
    2.42
    ك
    1.68
    i
    1.63
    ak
    1.44
    та
    1.43
    ى
    1.41
    ке
    1.40
    ри
    1.37
    c
    1.37
    да
    1.29
    Activations Density 0.001%

    No Known Activations