© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108582
    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_2_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
    ル
    1.41
    ل
    1.40
    ל
    1.18
    사
    1.13
    ない
    1.10
    มี
    1.05
    ล
    1.05
    ᱘
    1.04
    מו
    1.00
    わ
    1.00
    POSITIVE LOGITS
    ين
    1.07
     in
    1.06
    ah
    1.04
    ost
    0.92
    um
    0.89
    iy
    0.89
    g
    0.88
    ,
    0.88
     في
    0.87
    aya
    0.86
    Activations Density 0.000%

    No Known Activations