© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205777
    Prev
    Next
    INDEX
    Explanations

    code examples or comments

    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_25_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
     necesitan
    0.35
     неожидан
    0.35
     понадоби
    0.35
    𝚔
    0.35
     próximo
    0.35
     چاہتے
    0.34
    生の
    0.34
     Larger
    0.34
     industriales
    0.33
     강
    0.33
    POSITIVE LOGITS
    number
    0.40
     connotations
    0.38
     number
    0.38
     Argos
    0.38
    AccountNumber
    0.38
     denoting
    0.37
     denars
    0.37
     admir
    0.37
    </img>
    0.36
    UER
    0.36
    Activations Density 0.000%

    No Known Activations