© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87740
    Prev
    Next
    INDEX
    Explanations

    Monoblock, MonoBehaviour, monospaced

    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
    п
    0.84
    .
    0.70
    ק
    0.69
    к
    0.68
    ى
    0.67
    稷
    0.65
    왜
    0.62
    و
    0.62
     поня
    0.59
     moverse
    0.59
    POSITIVE LOGITS
    t
    0.77
    kem
    0.71
    IS
    0.66
    ll
    0.65
    tte
    0.65
    kę
    0.64
    gable
    0.64
    0
    0.64
    cia
    0.64
    gister
    0.64
    Activations Density 0.004%

    No Known Activations