© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9265
    Prev
    Next
    INDEX
    Explanations

    is the

    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
    ala
    0.21
    之道
    0.20
    zo
    0.20
    ö
    0.20
    il
    0.19
     অয়েল
    0.19
    豢
    0.19
    öra
    0.19
     luật
    0.19
    शासन
    0.19
    POSITIVE LOGITS
    mathrm
    0.22
    ності
    0.20
    gruppen
    0.20
    在
    0.19
    ्ह
    0.18
     fossero
    0.18
     להיות
    0.18
    oğlu
    0.18
    сь
    0.18
     если
    0.18
    Activations Density 0.085%

    No Known Activations