© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 151186
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    bigr
    0.39
    rrr
    0.35
    hevik
    0.35
    ราะ
    0.34
    텍
    0.33
    իր
    0.33
    nable
    0.33
     decorate
    0.32
    ޤ
    0.32
    craft
    0.32
    POSITIVE LOGITS
    ober
    0.54
    tery
    0.54
    ucky
    0.53
    udes
    0.53
    OBER
    0.53
    igue
    0.52
    chers
    0.51
    izens
    0.51
    ̬
    0.51
    rition
    0.50
    Activations Density 0.007%

    No Known Activations