© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54323
    Prev
    Next
    INDEX
    Explanations

    tomorrow

    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_55_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
     gestern
    0.42
     Teles
    0.42
    atie
    0.38
     yesterday
    0.38
    엊
    0.36
    yester
    0.34
    vas
    0.33
     вчера
    0.33
    캥
    0.33
    꿩
    0.33
    POSITIVE LOGITS
     tom
    2.66
     tod
    2.25
     Tod
    2.20
    Tod
    2.14
    tom
    2.13
    Tom
    2.08
     Tom
    2.05
    tod
    2.02
     ton
    1.91
     TOM
    1.90
    Activations Density 0.158%

    No Known Activations