© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84399
    Prev
    Next
    INDEX
    Explanations

    DIY projects and ethos

    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_0_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
    ’
    1.91
    ק
    1.49
    '
    1.45
    า
    1.38
    ক
    1.30
    ע
    1.30
    יה
    1.30
    も
    1.30
    ле
    1.26
    ী
    1.25
    POSITIVE LOGITS
    {
    1.26
    ed
    1.24
    for
    1.23
    <0xB9>
    1.12
    enn
    1.10
    ين
    1.08
     immobili
    1.04
    ها
    1.02
    <0x80>
    1.01
    itts
    1.00
    Activations Density 0.001%

    No Known Activations