© 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. 7535
    Prev
    Next
    INDEX
    Explanations

    Tepe, Fusius, Dukes, Museum, Black, Carp, Savage, Shark

    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
     lưới
    0.50
    զ
    0.48
    xon
    0.48
    通常の
    0.48
    என்
    0.47
    .‏
    0.47
    xlab
    0.47
    ier
    0.45
     साहस
    0.45
     অনুষ্ঠ
    0.44
    POSITIVE LOGITS
    ie
    0.44
    ло
    0.44
    ی
    0.44
     deformation
    0.42
    یه
    0.42
    ں
    0.42
    TAL
    0.41
    щий
    0.40
     sog
    0.40
    рный
    0.40
    Activations Density 0.000%

    No Known Activations