© 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. 141995
    Prev
    Next
    INDEX
    Explanations

    alterna / alterno / alternativas

    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
    s
    1.73
    d
    1.52
    ب
    1.49
    cs
    1.48
    can
    1.43
    ле
    1.41
    基本
    1.40
    dengan
    1.38
    ა
    1.38
    ти
    1.32
    POSITIVE LOGITS
     that
    1.41
    5
    1.38
    I
    1.28
    ick
    1.26
    ↵
    1.23
    </strong>
    1.23
    iger
    1.21
    1
    1.20
    </u>
    1.19
     precarious
    1.17
    Activations Density 0.000%

    No Known Activations