© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79132
    Prev
    Next
    INDEX
    Explanations

    requests for action

    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_31_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
    岳
    0.37
     受
    0.36
     TU
    0.35
    동안
    0.35
     ರೋ
    0.35
     Boring
    0.34
    꾸
    0.34
     frightened
    0.34
     TNF
    0.34
    缑
    0.34
    POSITIVE LOGITS
    bicycle
    0.38
    defaultValue
    0.38
    vens
    0.38
     defaultValue
    0.38
     emanc
    0.37
    credit
    0.37
     klinik
    0.37
    asText
    0.37
    vd
    0.37
     වඩා
    0.37
    Activations Density 0.008%

    No Known Activations