© 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
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8701
    Prev
    Next
    INDEX
    Explanations

    merchandise trade and retail units

    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
    પણે
    2.70
    ير
    2.46
    heid
    2.38
     anlam
    2.32
    این
    2.31
    𝔬
    2.30
    酐
    2.24
    𝙮
    2.18
     antecedent
    2.18
    𝙢
    2.18
    POSITIVE LOGITS
    useEffect
    2.88
    🩰
    2.41
    ಪಡ
    2.32
    rd
    2.21
     Molecule
    2.21
    ْم
    2.19
    ことになる
    2.17
    se
    2.16
    سازی
    2.15
     sempat
    2.13
    Activations Density 0.022%

    No Known Activations