© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257577
    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_10_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
    ch
    1.27
    ו
    1.21
    an
    1.17
    big
    1.10
     residences
    1.09
    chin
    1.08
    ec
    1.07
    Hi
    1.07
    ar
    1.07
    9
    1.06
    POSITIVE LOGITS
    μένη
    1.37
    ्‍यादा
    1.36
    𝐬
    1.32
    ußer
    1.31
    硣
    1.27
    Ⲁ
    1.24
    SOCKET
    1.23
     Expt
    1.21
    кә
    1.21
    merksamkeit
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.