© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58345
    Prev
    Next
    INDEX
    Explanations

    child related phrases

    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_2_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
    션을
    1.12
    ０
    1.10
    čky
    1.07
    ınız
    1.05
    1.02
     utilizz
    0.99
    𝟎
    0.95
    dır
    0.95
    0.91
    0
    0.89
    POSITIVE LOGITS
    1
    1.94
    ن
    1.60
    ب
    1.57
    an
    1.56
    خ
    1.56
    ت
    1.50
    ח
    1.50
    il
    1.47
    ۱
    1.45
    ur
    1.42
    Activations Density 0.007%

    No Known Activations