© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17379
    Prev
    Next
    INDEX
    Explanations

    Build version or number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     différence
    0.41
    getString
    0.36
    迎
    0.36
     systém
    0.35
     system
    0.35
     Connectivity
    0.35
     protocolos
    0.35
     Utilizamos
    0.35
    Carlos
    0.34
     आरा
    0.34
    POSITIVE LOGITS
     Seals
    0.44
    zień
    0.41
    зен
    0.39
     unten
    0.38
     సీ
    0.38
    cia
    0.38
    钤
    0.37
     jis
    0.37
    essentially
    0.37
     Fielding
    0.36
    Activations Density 0.000%

    No Known Activations