© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44924
    Prev
    Next
    INDEX
    Explanations

    one-stop shop

    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_3_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
     stopping
    0.88
     stopped
    0.84
    м
    0.79
    ம்
    0.75
     $\
    0.73
     detener
    0.73
    م
    0.73
    ed
    0.72
    ו
    0.72
     for
    0.70
    POSITIVE LOGITS
    ra
    0.76
    ),
    0.74
    st
    0.70
    )।
    0.68
    rf
    0.66
    )،
    0.65
    },
    0.65
    ],
    0.63
    h
    0.63
    ruppe
    0.63
    Activations Density 0.002%

    No Known Activations