© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258420
    Prev
    Next
    INDEX
    Explanations

    ix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     aportan
    1.14
     đào
    1.12
     Abbreviations
    1.01
     Adapun
    1.01
    ፂ
    1.00
    деа
    1.00
    䥑
    0.99
     contraseña
    0.99
     complej
    0.99
    鬯
    0.98
    POSITIVE LOGITS
    g
    0.90
    t
    0.90
    tar
    0.86
    un
    0.85
     ng
    0.84
     and
    0.83
    st
    0.83
    tf
    0.82
    and
    0.82
    NO
    0.78
    Activations Density 0.000%

    No Known Activations