© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3223
    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_5_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
     эки
    1.37
     cơ
    1.36
    OTROS
    1.27
     летом
    1.26
     imaginations
    1.25
    맞
    1.25
    )\|_{
    1.25
     एनिमल्स
    1.23
     Partizan
    1.21
     čega
    1.20
    POSITIVE LOGITS
    i
    1.10
    isola
    1.06
    луйста
    1.04
     Esso
    1.01
     misuse
    0.99
     luxuri
    0.98
    Leg
    0.98
     onset
    0.96
     حر
    0.96
    Duty
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.