© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5698
    Prev
    Next
    INDEX
    Explanations

    a followed by t, r, b, c, m, d

    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
     hailing
    2.84
     topping
    2.58
     feest
    2.52
     chatter
    2.48
    𝓻
    2.42
    деся
    2.42
    活用
    2.40
    𝔂
    2.36
     isometry
    2.36
    ̺
    2.36
    POSITIVE LOGITS
    an
    2.69
    ра
    2.60
    م
    2.38
    le
    2.36
    場合の
    2.22
    一个是
    2.20
     ventre
    2.15
    اء
    2.13
    里
    2.12
    overs
    2.11
    Activations Density 0.027%

    No Known Activations