© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93571
    Prev
    Next
    INDEX
    Explanations

    uppercase letters

    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_60_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
    s
    0.50
    m
    0.42
     scept
    0.36
    c
    0.36
     ste
    0.35
    sht
    0.35
     m
    0.34
     stries
    0.33
    sby
    0.33
     spr
    0.33
    POSITIVE LOGITS
     G
    1.16
     J
    1.12
     F
    1.09
     B
    1.09
     W
    1.05
     A
    1.02
     H
    1.01
     P
    0.99
     E
    0.98
     K
    0.98
    Activations Density 0.007%

    No Known Activations