© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6319
    Prev
    Next
    INDEX
    Explanations

    security

    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_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
    ../
    2.44
    क
    2.42
    ir
    2.36
    ிட
    2.32
    \{(
    2.31
    )}"
    2.26
    )^*
    2.26
    ி
    2.23
    redu
    2.22
    стоя
    2.20
    POSITIVE LOGITS
    ী
    3.30
     tarjetas
    2.64
    𝐿
    2.49
     păr
    2.47
    𝑒
    2.46
     gep
    2.41
     vrem
    2.40
     membutuhkan
    2.35
     ogen
    2.29
     hưởng
    2.29
    Activations Density 0.001%

    No Known Activations