© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3335
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    as
    3.15
    য়
    2.75
    у
    2.70
    د
    2.68
    ि
    2.65
     regard
    2.55
    е
    2.53
    ف
    2.53
    aler
    2.52
    お手
    2.52
    POSITIVE LOGITS
    CTIONS
    3.00
    BIUM
    2.99
    itary
    2.94
    ities
    2.94
    ங்கிணை
    2.84
    <unused249>
    2.83
    ు
    2.80
    UAGES
    2.65
    fection
    2.64
     exploiting
    2.55
    Activations Density 0.006%

    No Known Activations