© 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. 169939
    Prev
    Next
    INDEX
    Explanations

    say "be" or state

    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
    otipos
    0.37
    לח
    0.36
    ungkan
    0.36
    apan
    0.35
    ograma
    0.35
    itipi
    0.34
     пан
    0.34
    琪
    0.33
    齧
    0.33
     META
    0.33
    POSITIVE LOGITS
     dil
    2.05
     daw
    1.65
    Dil
    1.53
     Dil
    1.49
    dil
    1.48
     Daw
    1.31
    Daw
    1.25
     lo
    1.23
    daw
    1.20
     dilation
    1.15
    Activations Density 0.003%

    No Known Activations