© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160499
    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
     in
    1.44
    يا
    1.07
    ق
    0.95
     I
    0.95
    ную
    0.91
    بية
    0.90
     في
    0.89
     estern
    0.88
     préférable
    0.84
     émotion
    0.84
    POSITIVE LOGITS
    et
    1.72
    a
    1.59
    ه
    1.58
    া
    1.33
    el
    1.30
    ار
    1.23
    '
    1.20
    )
    1.20
    :
    1.18
    ag
    1.09
    Activations Density 0.000%

    No Known Activations