© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229887
    Prev
    Next
    INDEX
    Explanations

    Dino

    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_6_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
    ని
    1.06
     I
    1.00
    <0xAB>
    0.84
    !");
    0.82
    一些
    0.76
     ejac
    0.74
    懂得
    0.73
     weist
    0.73
     you
    0.72
    !\
    0.72
    POSITIVE LOGITS
    a
    1.73
    ac
    1.43
    ס
    1.41
    ul
    1.33
    un
    1.32
    ou
    1.28
    am
    1.28
    k
    1.24
    ap
    1.18
    he
    1.17
    Activations Density 0.000%

    No Known Activations