© 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. 43144
    Prev
    Next
    INDEX
    Explanations

    content writer, length

    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
    )
    0.80
     في
    0.79
    ל
    0.75
    ]
    0.71
     در
    0.69
     използ
    0.68
     σε
    0.68
    )=>
    0.68
    ),
    0.66
    ):
    0.66
    POSITIVE LOGITS
    re
    0.82
    y
    0.78
    AM
    0.73
    il
    0.73
    is
    0.72
    ISE
    0.71
    m
    0.71
    ACH
    0.70
    I
    0.68
    EN
    0.67
    Activations Density 0.002%

    No Known Activations