© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208415
    Prev
    Next
    INDEX
    Explanations

    Components

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    left
    0.48
    Left
    0.47
     left
    0.44
    Works
    0.42
     izquierda
    0.40
    左
    0.40
    works
    0.38
     Left
    0.38
     seguidores
    0.38
    this
    0.37
    POSITIVE LOGITS
     সাধারণত
    0.42
     solito
    0.41
     retrouvé
    0.41
     عادة
    0.41
     strengthened
    0.41
     aidant
    0.41
     $:
    0.40
     usually
    0.40
     обычно
    0.40
    也将
    0.40
    Activations Density 0.008%

    No Known Activations