© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67996
    Prev
    Next
    INDEX
    Explanations

    subjective

    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_51_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
     Too
    0.44
    Too
    0.44
    Lith
    0.43
    锂
    0.43
     października
    0.42
    太
    0.41
    too
    0.39
     TOO
    0.38
    fti
    0.38
    ́
    0.38
    POSITIVE LOGITS
    ၉
    0.42
     N
    0.41
    ativo
    0.40
    nol
    0.40
     ಕೊ
    0.39
     space
    0.39
    ്ര
    0.39
     brightness
    0.39
    bergs
    0.39
    atas
    0.38
    Activations Density 0.004%

    No Known Activations