© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197012
    Prev
    Next
    INDEX
    Explanations

    peak and power

    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_4_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
    '
    0.65
    -
    0.64
    >
    0.64
    (
    0.55
    ’
    0.55
    sh
    0.51
    *
    0.51
    +
    0.51
    ‘
    0.51
     be
    0.51
    POSITIVE LOGITS
    Aslamualaikum
    0.48
     dinast
    0.47
    기
    0.47
    ᱕
    0.47
    striatis
    0.46
    ઠળ
    0.46
     humains
    0.46
    궬
    0.44
    럇
    0.44
     الدین
    0.44
    Activations Density 0.004%

    No Known Activations