© 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. 7168
    Prev
    Next
    INDEX
    Explanations

    numbers like 2.7

    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
    +}^{
    1.25
     }}(\
    1.21
     znale
    1.19
     самое
    1.18
     seno
    1.17
    ๆ
    1.17
    ijska
    1.15
    *((*
    1.15
    \}.
    1.14
    ########
    1.12
    POSITIVE LOGITS
    ت
    1.86
     nerveux
    1.43
    к
    1.42
    ה
    1.37
    ğini
    1.31
    ע
    1.30
    不高
    1.29
     Presence
    1.26
     인해
    1.26
    ط
    1.25
    Activations Density 0.056%

    No Known Activations