© 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. 159111
    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
    el
    1.37
    le
    1.31
    \
    1.24
    at
    1.13
    led
    1.12
    la
    1.10
    َ
    1.09
     to
    1.08
    ra
    1.05
    ão
    1.04
    POSITIVE LOGITS
    ק
    1.37
    Idioma
    1.18
    دی
    1.17
    ፣
    1.16
     katva
    1.15
    ג
    1.13
    できる
    1.09
     kammam
    1.09
     sabbam
    1.08
    f
    1.07
    Activations Density 0.000%

    No Known Activations