© 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-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147049
    Prev
    Next
    INDEX
    Explanations

    in or out

    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_18_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
    尔
    0.23
    puri
    0.22
    lement
    0.21
     toy
    0.21
    ycle
    0.21
     delayed
    0.21
    ferm
    0.21
     होने
    0.21
    ske
    0.21
    ed
    0.20
    POSITIVE LOGITS
     katika
    0.23
    ᖏ
    0.23
     makalah
    0.22
     pripre
    0.22
     прикла
    0.22
     Миха
    0.21
    Bella
    0.21
    kah
    0.21
     disadvant
    0.21
    ریز
    0.21
    Activations Density 0.005%

    No Known Activations