© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214962
    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_5_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
    0
    1.77
    I
    1.12
    ther
    1.06
    ney
    1.04
    fee
    1.03
    ın
    0.99
    _
    0.99
     I
    0.97
    1
    0.96
    bro
    0.96
    POSITIVE LOGITS
    ו
    1.66
    い
    1.64
    ל
    1.56
    ل
    1.53
    મ
    1.47
    자
    1.46
    ை
    1.45
    ल
    1.44
    ي
    1.42
    ف
    1.41
    Activations Density 0.000%

    No Known Activations