© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106200
    Prev
    Next
    INDEX
    Explanations

    demos

    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_1_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
    I
    1.84
    )
    1.80
    ]
    1.71
    :
    1.58
    ')
    1.51
    '
    1.50
    \]
    1.41
    }
    1.36
    /
    1.36
     at
    1.33
    POSITIVE LOGITS
    in
    1.52
    ра
    1.52
    ly
    1.34
    ين
    1.32
    ap
    1.31
    ки
    1.30
    s
    1.27
    ية
    1.27
    ik
    1.24
    지
    1.24
    Activations Density 0.000%

    No Known Activations