© 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. 168772
    Prev
    Next
    INDEX
    Explanations

    in

    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
     b
    0.48
     б
    0.44
    b
    0.41
    <0x99>
    0.39
    ową
    0.38
     bure
    0.37
     cyberspace
    0.37
     bour
    0.37
     biel
    0.37
     ব
    0.37
    POSITIVE LOGITS
     (’
    0.40
    OPTION
    0.38
    MOTION
    0.38
    เวล
    0.38
     (‘
    0.37
    槤
    0.36
    eous
    0.34
    sø
    0.34
     चक्रवृद्धि
    0.34
     tops
    0.33
    Activations Density 0.000%

    No Known Activations