© 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. 169137
    Prev
    Next
    INDEX
    Explanations

    sc

    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
     sc
    0.47
     MIP
    0.41
    GEBURTSORT
    0.41
    ynos
    0.39
     Yal
    0.37
    硫
    0.37
     अा
    0.36
     st
    0.36
     YAP
    0.36
     Koh
    0.36
    POSITIVE LOGITS
     nurses
    0.43
     вот
    0.42
     outre
    0.39
     scans
    0.38
     analyses
    0.37
    izas
    0.37
     பாதிக்கப்பட்ட
    0.36
    ('(
    0.35
    eries
    0.35
     extracts
    0.35
    Activations Density 0.000%

    No Known Activations