© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11003
    Prev
    Next
    INDEX
    Explanations

    several ways

    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_13_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
     j
    0.32
     senseless
    0.30
     their
    0.30
     leur
    0.30
     você
    0.29
     THEIR
    0.29
     hypergly
    0.29
    ij
    0.29
    idding
    0.28
     on
    0.28
    POSITIVE LOGITS
    (
    0.37
    ף
    0.35
    То
    0.30
     पुढील
    0.30
    gten
    0.30
    ફ
    0.29
     frecuente
    0.29
    cary
    0.29
    cof
    0.29
    фа
    0.28
    Activations Density 0.051%

    No Known Activations