© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18167
    Prev
    Next
    INDEX
    Explanations

    get or receive

    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_34_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
     छिपा
    0.41
     builtin
    0.39
     छुपा
    0.38
    ślin
    0.37
    ジン
    0.37
    Viki
    0.36
     숨
    0.35
    伥
    0.35
     _$_
    0.35
     அம்பேத்க
    0.34
    POSITIVE LOGITS
    得到
    0.69
     получить
    0.67
     receive
    0.67
     bekommen
    0.65
    ได้รับ
    0.64
     received
    0.64
     erhalten
    0.64
    received
    0.64
     получение
    0.63
     får
    0.61
    Activations Density 0.108%

    No Known Activations