© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142797
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    wider
    0.53
    dL
    0.53
    g
    0.52
    로부터
    0.51
     بجائے
    0.51
    lensFlare
    0.50
    せず
    0.50
    ين
    0.48
    біць
    0.48
    楍
    0.48
    POSITIVE LOGITS
     leading
    0.46
     sourceType
    0.43
    am
    0.42
     Chemical
    0.42
     வாக
    0.42
    Leading
    0.41
    amins
    0.40
    节奏
    0.40
     moisturizing
    0.40
    是真的
    0.39
    Activations Density 0.000%

    No Known Activations