© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137185
    Prev
    Next
    INDEX
    Explanations

    LaTeX documents

    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_12_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
    tte
    0.31
    abilă
    0.30
    ca
    0.29
    bokeh
    0.29
    aga
    0.29
    ?>
    0.28
    ONS
    0.28
    专注于
    0.28
    ämme
    0.28
    一种
    0.27
    POSITIVE LOGITS
    <0x80>
    0.30
    न्दर
    0.29
    ):["
    0.28
     Iyer
    0.27
     අධ
    0.27
     ಉತ್ತ
    0.27
     வெற்றிய
    0.27
     ಅಥವಾ
    0.26
     controlar
    0.25
     Wasn
    0.25
    Activations Density 0.000%

    No Known Activations