© 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. 61547
    Prev
    Next
    INDEX
    Explanations

    ab leading words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    )
    1.34
    o
    1.11
    ني
    1.05
    ]
    1.05
    ă
    1.04
     eine
    0.99
    )」
    0.96
     ouder
    0.96
    }
    0.96
     in
    0.95
    POSITIVE LOGITS
    یا
    1.09
    un
    1.04
    AR
    1.03
    ری
    1.03
    watering
    1.03
    у
    1.03
    ON
    1.02
    ्त
    1.02
    н
    1.01
    та
    1.00
    Activations Density 0.000%

    No Known Activations