© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21254
    Prev
    Next
    INDEX
    Explanations

    late

    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_56_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
     late
    3.84
     Late
    3.52
    Late
    3.52
    late
    3.44
    晚
    2.58
     позд
    2.30
    늦
    2.30
     देर
    2.23
     tard
    2.17
     spät
    1.97
    POSITIVE LOGITS
    掮
    0.39
     اولیه
    0.38
    বায়
    0.38
    шкина
    0.35
    <unused52>
    0.33
    bilir
    0.33
    ීන්
    0.33
    uld
    0.32
     plead
    0.32
    episode
    0.31
    Activations Density 0.022%

    No Known Activations