© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8133
    Prev
    Next
    INDEX
    Explanations

    imagery

    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_40_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
    ებთ
    0.36
     Faye
    0.35
     Mug
    0.34
    clerotic
    0.34
    トゥーン
    0.34
    떄
    0.34
    \<^
    0.34
     censor
    0.33
    姪
    0.33
    дит
    0.33
    POSITIVE LOGITS
     imagery
    0.75
    imagery
    0.64
    Imagery
    0.62
     Imagery
    0.58
    ERY
    0.52
    ery
    0.52
    istry
    0.49
    estry
    0.46
    ISTRY
    0.44
    inery
    0.43
    Activations Density 0.116%

    No Known Activations