© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164896
    Prev
    Next
    INDEX
    Explanations

    secret keys or visa numbers

    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_13_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
    ли
    0.56
    uming
    0.55
    umption
    0.52
    сс
    0.48
    -
    0.48
    加热
    0.47
    inah
    0.46
    iare
    0.45
    лений
    0.44
    um
    0.44
    POSITIVE LOGITS
     aband
    0.50
     ascenso
    0.49
    )：
    0.47
     VISA
    0.47
     antiguos
    0.46
    ﺖ
    0.46
    nombre
    0.45
     derece
    0.44
    ﻚ
    0.44
     visa
    0.44
    Activations Density 0.000%

    No Known Activations