© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34281
    Prev
    Next
    INDEX
    Explanations

    The Wall Street Journal

    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
    ளும்
    0.60
    я
    0.56
    িতে
    0.53
     stony
    0.53
     Shakespeare
    0.53
            
    0.52
    拉
    0.51
     Länder
    0.50
                          
    0.50
    輋
    0.50
    POSITIVE LOGITS
    c
    0.99
    b
    0.93
    z
    0.79
     със
    0.75
    dans
    0.73
    ید
    0.73
    T
    0.73
    fda
    0.72
    de
    0.72
    ዱ
    0.71
    Activations Density 0.001%

    No Known Activations