© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1793
    Prev
    Next
    INDEX
    Explanations

    four

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    八
    0.52
    <0xB9>
    0.49
     eight
    0.49
     আট
    0.46
     oito
    0.45
     вось
    0.44
     huit
    0.43
    eight
    0.42
    Eight
    0.42
     आठ
    0.42
    POSITIVE LOGITS
    𝟰
    0.52
    ៤
    0.49
     चौथे
    0.48
    4
    0.46
    ₄
    0.46
    ４
    0.45
     fourth
    0.45
    ٤
    0.45
     ten
    0.45
     Ten
    0.44
    Activations Density 0.039%

    No Known Activations