© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    healthy fats

    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
    UAGES
    2.95
    itore
    2.53
    𝚍
    2.51
    at
    2.49
    াঙ্গীর
    2.44
    irection
    2.43
     traverses
    2.41
    辦法
    2.38
    ത്ഥ
    2.34
    $",
    2.32
    POSITIVE LOGITS
    м
    3.58
    Ф
    3.09
    情况下
    2.52
    ΤΟ
    2.46
    quantile
    2.37
     thighs
    2.35
    ဴ
    2.33
     recursion
    2.32
     baryons
    2.31
     histó
    2.30
    Activations Density 0.058%

    No Known Activations