© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89977
    Prev
    Next
    INDEX
    Explanations

    early time

    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_60_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
    little
    0.57
     little
    0.57
     poco
    0.52
    Little
    0.48
     pouco
    0.45
    8
    0.45
     wenig
    0.44
    9
    0.44
    3
    0.43
    4
    0.42
    POSITIVE LOGITS
     early
    0.86
    early
    0.79
    早
    0.68
     EARLY
    0.64
     früh
    0.57
    Early
    0.57
     Nov
    0.56
     Oct
    0.54
     temprana
    0.54
    早期
    0.53
    Activations Density 0.004%

    No Known Activations