© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82936
    Prev
    Next
    INDEX
    Explanations

    WebDriverWait, Jarvis, foreign scripts

    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_0_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
     for
    1.24
     (
    1.20
    zione
    1.06
    ;
    1.06
    uk
    1.05
     phasing
    1.05
     irreducible
    1.05
    ere
    1.04
     the
    1.02
     fuselage
    1.02
    POSITIVE LOGITS
    و
    2.00
    ة
    1.62
    ו
    1.62
    ت
    1.60
    కు
    1.51
    اب
    1.49
    ка
    1.45
    ام
    1.45
    ید
    1.45
    ેટ
    1.44
    Activations Density 0.000%

    No Known Activations