© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82592
    Prev
    Next
    INDEX
    Explanations

    conditional

    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_53_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
    なければ
    0.38
     הי
    0.38
    ཧ
    0.36
     Runde
    0.36
    FileVersion
    0.36
    рыма
    0.35
    Trusted
    0.35
    Demi
    0.35
     overwhelmed
    0.35
     snuff
    0.35
    POSITIVE LOGITS
    irió
    0.43
    र्वाद
    0.37
     Muscles
    0.34
    Ｇ
    0.33
    GeV
    0.33
    łek
    0.33
    ressions
    0.32
     o
    0.31
    ّه
    0.31
    βολ
    0.31
    Activations Density 0.002%

    No Known Activations