© 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. 207223
    Prev
    Next
    INDEX
    Explanations

    Here

    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
     inc
    0.47
     isnt
    0.45
    Senior
    0.45
     incorporates
    0.41
    nows
    0.41
    ims
    0.39
    }:=
    0.38
     Senior
    0.38
    なんて
    0.37
     brings
    0.37
    POSITIVE LOGITS
    ’
    0.44
    '
    0.40
    ‟
    0.39
     hivyo
    0.38
    Ꞌ
    0.36
    뿍
    0.35
    '_{\
    0.35
     crowds
    0.33
    èces
    0.33
     vậy
    0.33
    Activations Density 0.012%

    No Known Activations