© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9366
    Prev
    Next
    INDEX
    Explanations

    technical or code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    **/
    1.12
    \"\
    1.03
    **:
    0.98
    ,’’
    0.97
    🔸
    0.97
    **,
    0.96
    ⁣
    0.94
     **/
    0.94
    **)
    0.92
     "**
    0.92
    POSITIVE LOGITS
    ريح
    0.63
    మైన
    0.62
     kohta
    0.61
    arlin
    0.61
     czego
    0.59
     bieg
    0.59
    IES
    0.58
    ozems
    0.58
    undet
    0.57
     분위
    0.57
    Activations Density 1.269%

    No Known Activations