© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89724
    Prev
    Next
    INDEX
    Explanations

    replication fork association

    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_18_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
    urken
    0.44
    CLUSTERED
    0.44
    몫
    0.43
     ’’
    0.43
    again
    0.43
    abut
    0.43
     ακόμη
    0.42
    ومة
    0.40
    acd
    0.40
    astern
    0.40
    POSITIVE LOGITS
    >,
    0.55
     Ку
    0.47
     регули
    0.46
     permitir
    0.45
     グ
    0.45
     consciente
    0.44
    >.
    0.44
     ug
    0.44
     Parlamento
    0.44
     Rest
    0.43
    Activations Density 0.000%

    No Known Activations