© 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. 142442
    Prev
    Next
    INDEX
    Explanations

    hierarch or surviv ability

    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
    as
    2.08
    an
    1.96
    is
    1.88
    er
    1.78
    es
    1.73
    ul
    1.71
    ма
    1.59
    ↵↵
    1.57
    ing
    1.55
    he
    1.53
    POSITIVE LOGITS
    ।
    1.64
     I
    1.59
    。
    1.56
    ও
    1.43
    )،
    1.41
    ។
    1.39
    )।
    1.35
    }.
    1.27
    ),
    1.26
    もら
    1.25
    Activations Density 0.000%

    No Known Activations