© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154038
    Prev
    Next
    INDEX
    Explanations

    llama, alpaca, vicuna

    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_23_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
    છ
    0.40
     concepts
    0.35
    はない
    0.35
    mont
    0.34
    ᄋ
    0.34
     modific
    0.33
     appropriation
    0.33
     benefit
    0.33
     budget
    0.32
     lift
    0.32
    POSITIVE LOGITS
    
    0.38
    톄
    0.36
     குழந்தைகள்
    0.36
     Kindern
    0.36
    एसआई
    0.36
    สัย
    0.35
    াস্থ্য
    0.35
     आरमारा
    0.35
     النساء
    0.34
     รอบ
    0.34
    Activations Density 0.000%

    No Known Activations