© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36984
    Prev
    Next
    INDEX
    Explanations

    chegg, informatics, cheesy

    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_3_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
    is
    0.82
    та
    0.78
    na
    0.75
    ta
    0.75
    {
    0.68
    ти
    0.66
    0.65
    ik
    0.63
     SHIPPING
    0.63
    int
    0.62
    POSITIVE LOGITS
     on
    0.70
    其他
    0.66
    إ
    0.64
     ইঞ্জ
    0.64
     Công
    0.63
    டன
    0.62
    е
    0.62
    ה
    0.62
    هم
    0.61
    pictureBox
    0.61
    Activations Density 0.001%

    No Known Activations