© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 7346
    Prev
    Next
    INDEX
    Explanations

    code function declarations

    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
    е
    2.75
    ㅉ
    2.37
     রকম
    2.28
    о
    2.24
     Benutz
    2.22
     الكريم
    2.20
     sitten
    2.13
    upaten
    2.10
     incurring
    2.07
     Hye
    2.04
    POSITIVE LOGITS
    ত্ব
    2.44
    resión
    2.35
    ihe
    2.32
     څنګه
    2.29
    μένο
    2.26
    ruire
    2.21
    𝙡
    2.20
    ሦ
    2.16
    েও
    2.16
    am
    2.14
    Activations Density 0.001%

    No Known Activations