© 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. 60156
    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
     (
    1.48
     was
    1.21
    1.19
     is
    1.14
    ли
    1.10
    -
    1.08
    س
    1.08
    ]
    1.05
     or
    1.02
     can
    1.02
    POSITIVE LOGITS
    2
    1.27
    𝗯
    1.11
    on
    1.10
    7
    1.08
    йти
    1.03
    tų
    1.02
    m
    1.02
    ম
    0.99
    ja
    0.99
     crebre
    0.96
    Activations Density 0.000%

    No Known Activations