© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 43926
    Prev
    Next
    INDEX
    Explanations

    think carefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ו
    1.05
     arrêté
    0.90
     allez
    0.82
    el
    0.79
    esse
    0.76
     escrib
    0.76
     écriv
    0.76
     animé
    0.76
    er
    0.75
    ent
    0.75
    POSITIVE LOGITS
    t
    1.02
    ton
    0.72
    theta
    0.72
    total
    0.68
    treated
    0.68
    tz
    0.67
    train
    0.67
    tcp
    0.67
    да
    0.66
    training
    0.66
    Activations Density 0.009%

    No Known Activations