© 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-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 165820
    Prev
    Next
    INDEX
    Explanations

    URL identifiers and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     infecting
    0.39
    ້ອ
    0.39
     frutos
    0.39
    𝘭
    0.39
     informée
    0.37
    дун
    0.36
    蛹
    0.36
    的目的
    0.36
    Alam
    0.36
    ڵ
    0.36
    POSITIVE LOGITS
     bat
    0.38
     Bat
    0.37
     কার্যক্রম
    0.34
     মালিক
    0.33
    Bat
    0.33
    Kf
    0.33
     والدین
    0.33
     Koff
    0.33
    ogether
    0.33
     меры
    0.33
    Activations Density 0.000%

    No Known Activations