© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43969
    Prev
    Next
    INDEX
    Explanations

    rundown of

    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
    F
    0.65
     la
    0.64
    ene
    0.60
     foreigner
    0.58
    ethe
    0.58
    akam
    0.58
    ick
    0.57
     Gonzaga
    0.56
    ora
    0.55
    \$
    0.55
    POSITIVE LOGITS
    ا
    1.57
    ה
    1.35
    ל
    1.23
    ه
    1.08
    n
    1.07
    ل
    1.01
    a
    0.99
    ب
    0.94
    на
    0.93
    at
    0.92
    Activations Density 0.013%

    No Known Activations