© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175529
    Prev
    Next
    INDEX
    Explanations

    date formatting string

    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_20_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
    koord
    0.22
    igraf
    0.21
    fordern
    0.20
    熬
    0.20
    जफ्फर
    0.20
    blings
    0.20
     Rafi
    0.20
    balik
    0.20
    jn
    0.20
     roughly
    0.19
    POSITIVE LOGITS
     добав
    0.22
     `=`,
    0.21
     ชั้น
    0.21
     '*
    0.20
     protecting
    0.20
     extending
    0.20
     gleiche
    0.20
    สน
    0.20
    强化
    0.20
    ורה
    0.19
    Activations Density 0.007%

    No Known Activations