© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247963
    Prev
    Next
    INDEX
    Explanations

    box

    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
    Negative Logits
     says
    2.42
     Says
    2.31
    Says
    2.28
    says
    2.19
     say
    1.84
     säger
    1.70
    说
    1.70
     siger
    1.67
     يقول
    1.64
     zegt
    1.64
    POSITIVE LOGITS
     }}-
    0.36
    ierten
    0.35
    滢
    0.34
    াচিত
    0.34
     signUp
    0.34
    젝
    0.34
     بمعنى
    0.34
     föld
    0.33
    resents
    0.33
    isVideoRecording
    0.33
    Activations Density 0.004%

    No Known Activations