© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214912
    Prev
    Next
    INDEX
    Explanations

    assumptions

    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_5_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
    BC
    1.86
    CD
    1.81
    ES
    1.80
    TE
    1.76
    AL
    1.73
    DF
    1.71
    ’
    1.71
    AV
    1.70
    DA
    1.70
    CI
    1.69
    POSITIVE LOGITS
    。
    1.35
    ،
    1.31
    да
    1.25
    し
    1.22
     I
    1.20
    ма
    1.20
    、
    1.12
    τα
    1.09
    ၊
    1.09
    <0x0D>
    1.07
    Activations Density 0.005%

    No Known Activations