© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250446
    Prev
    Next
    INDEX
    Explanations

    =

    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
     ph
    0.39
    constant
    0.39
     lenses
    0.38
     Constant
    0.37
     constant
    0.36
     Const
    0.36
    Constant
    0.35
    $=\
    0.35
     const
    0.34
     constantes
    0.34
    POSITIVE LOGITS
    瑗
    0.41
    •
    0.38
    Dear
    0.37
    Guest
    0.37
    Fur
    0.35
    茣
    0.35
     •
    0.34
    ㆍ
    0.34
    }">
    0.34
     □
    0.34
    Activations Density 0.000%

    No Known Activations