© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65661
    Prev
    Next
    INDEX
    Explanations

    the letter I

    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
     ATA
    0.42
     передви
    0.40
    ATA
    0.39
    aset
    0.38
    atas
    0.38
    Ｑ
    0.37
    ata
    0.37
    orem
    0.36
     ste
    0.36
     Battle
    0.36
    POSITIVE LOGITS
    Bo
    0.41
    рый
    0.38
     correspondent
    0.38
    crab
    0.37
    ხ
    0.37
     корреспонд
    0.36
    шире
    0.36
    적이
    0.36
     décerné
    0.36
    ள்
    0.36
    Activations Density 0.002%

    No Known Activations