© 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. 157567
    Prev
    Next
    INDEX
    Explanations

    access modifiers, prompts, or grammatical

    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
    ри
    1.63
    ה
    1.32
    ت
    1.31
    y
    1.17
    ە
    1.13
    وء
    1.12
    ه
    1.12
    이나
    1.05
    ),
    1.05
    وين
    1.02
    POSITIVE LOGITS
     as
    1.34
    し
    1.12
     añad
    1.05
    T
    1.03
    Y
    1.00
    ier
    0.98
     analiz
    0.98
     naveg
    0.96
     	i
    0.96
    ći
    0.95
    Activations Density 0.001%

    No Known Activations