© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    pointers and string handling

    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_40_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
    حال
    0.25
    கொ
    0.24
     التالي
    0.22
     असतील
    0.21
    लिड
    0.21
     nmea
    0.21
     ट्रा
    0.21
     ＜
    0.21
     EnglishChoose
    0.21
    \*
    0.21
    POSITIVE LOGITS
    рец
    0.23
     pointer
    0.23
     Pointer
    0.21
    द्य
    0.20
    டுக
    0.20
    сову
    0.20
    Pointer
    0.20
    ainty
    0.20
    ρέ
    0.19
     mortar
    0.19
    Activations Density 0.017%

    No Known Activations