© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5149
    Prev
    Next
    INDEX
    Explanations

    as st

    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
    ки
    3.02
    ר
    2.68
    ท์
    2.42
    ส์
    2.28
    น
    2.26
    ле
    2.26
    мо
    2.24
    ด์
    2.23
    __(
    2.20
    உ
    2.20
    POSITIVE LOGITS
     Οι
    2.79
     Belediyesi
    2.54
     negligence
    2.49
     Vicky
    2.38
     thence
    2.36
    ய்டா
    2.35
     perturbative
    2.34
     bhi
    2.34
    oppable
    2.30
    yilda
    2.29
    Activations Density 0.000%

    No Known Activations