© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170661
    Prev
    Next
    INDEX
    Explanations

    Pre

    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_56_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
    Ce
    0.65
     Ce
    0.59
    ce
    0.58
    CE
    0.55
     c
    0.53
     Це
    0.52
     CE
    0.50
    Cecil
    0.47
    C
    0.46
    pole
    0.46
    POSITIVE LOGITS
     pre
    0.47
     preorder
    0.46
     pré
    0.43
     Pré
    0.42
    、『
    0.42
     preload
    0.41
     Präsident
    0.41
     breeder
    0.40
     президен
    0.40
     Preheat
    0.39
    Activations Density 0.001%

    No Known Activations