© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258684
    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
    chars
    1.29
    vorsch
    1.21
    푚
    1.19
    ির
    1.18
    dalam
    1.15
     budú
    1.15
     будут
    1.14
     пото
    1.13
    losen
    1.13
    likle
    1.12
    POSITIVE LOGITS
     debilitating
    1.38
     scor
    1.22
    Judging
    1.18
     centrally
    1.16
    𝘦
    1.10
    ૂ
    1.08
    ම
    1.06
     maneira
    1.06
    𝘴
    1.06
     irresponsible
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.