© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138869
    Prev
    Next
    INDEX
    Explanations

    clothing items

    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_46_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
    丼
    0.38
    LException
    0.37
    เซีย
    0.37
    舒
    0.36
    लिट
    0.36
    ྫ
    0.36
    awab
    0.35
    POP
    0.35
    ógico
    0.35
    Comfort
    0.35
    POSITIVE LOGITS
     mel
    0.59
    meli
    0.50
     mar
    0.50
     Mel
    0.47
    mel
    0.46
     Mél
    0.46
    lectricité
    0.44
    Mel
    0.42
    ायक
    0.42
    烁
    0.42
    Activations Density 0.001%

    No Known Activations