© 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. 131074
    Prev
    Next
    INDEX
    Explanations

    JIRA, Jayson Tatum

    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
    ação
    1.09
    いたり
    0.98
    。
    0.93
    로
    0.93
    <0x80>
    0.91
    ه
    0.89
     sparingly
    0.88
    も
    0.88
     I
    0.88
    もら
    0.88
    POSITIVE LOGITS
    л
    1.54
    ב
    1.33
    b
    1.24
    లో
    1.23
    ü
    1.13
    w
    1.08
    li
    1.05
    SC
    1.04
    ת
    1.04
    ass
    1.03
    Activations Density 0.000%

    No Known Activations