© 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. 166900
    Prev
    Next
    INDEX
    Explanations

    know languages

    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
    few
    0.49
    △
    0.48
     few
    0.46
    Few
    0.45
     Few
    0.43
    longest
    0.41
     till
    0.39
     longest
    0.39
    차
    0.38
     △
    0.38
    POSITIVE LOGITS
     Know
    0.53
    Know
    0.52
     weten
    0.41
     KNOW
    0.40
     Knows
    0.40
     know
    0.40
     Reel
    0.39
     знаем
    0.38
     sapere
    0.37
    know
    0.37
    Activations Density 0.000%

    No Known Activations