© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 260207
    Prev
    Next
    INDEX
    Explanations

    place _ id

    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_10_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
     reproach
    0.43
    𒀊
    0.39
     defam
    0.39
     dhinak
    0.39
    𒆪
    0.36
    㡚
    0.36
    𒅀
    0.36
     stargazerCount
    0.35
     lackluster
    0.35
    𒄷
    0.35
    POSITIVE LOGITS
     or
    0.42
    ton
    0.39
     American
    0.36
     So
    0.36
     and
    0.35
    land
    0.35
    or
    0.34
     also
    0.34
    i
    0.33
    ar
    0.33
    Activations Density 0.003%

    No Known Activations