© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199270
    Prev
    Next
    INDEX
    Explanations

    's followed by descriptive nouns

    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_9_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
    :
    0.30
    {
    0.26
    ت
    0.26
    \{
    0.26
    kenalkan
    0.23
    렸
    0.23
    ের
    0.23
    <
    0.23
    نع
    0.22
    9
    0.22
    POSITIVE LOGITS
     l
    0.37
    are
    0.31
    io
    0.30
     بين
    0.30
    r
    0.30
    to
    0.29
    ul
    0.29
    re
    0.28
    ica
    0.27
    l
    0.27
    Activations Density 0.026%

    No Known Activations