© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5235
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical expressions

    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
    वर
    2.92
    ে
    2.40
    рою
    2.31
     insure
    2.30
     welche
    2.20
     Kamu
    2.18
     Opportun
    2.17
    ocalypse
    2.16
    ງ
    2.15
     gesamten
    2.13
    POSITIVE LOGITS
    𝑖
    2.45
    𝑎
    2.43
    𝑦
    2.39
    che
    2.36
     lordship
    2.29
    장
    2.24
    ′
    2.22
    gian
    2.19
    ่
    2.16
    ncbi
    2.13
    Activations Density 0.000%

    No Known Activations