© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129995
    Prev
    Next
    INDEX
    Explanations

    Newton's method (Newton-Raphson)

    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_6_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
    .
    0.99
     It
    0.96
    ]
    0.92
    )
    0.89
    UM
    0.89
    $
    0.86
    </h2>
    0.82
    PM
    0.82
    </u>
    0.81
     be
    0.80
    POSITIVE LOGITS
    ra
    1.32
    り
    1.24
     teeming
    1.21
     demean
    1.17
     Consultado
    1.15
    தி
    1.14
    να
    1.12
    のない
    1.12
    ла
    1.11
    வுக்கு
    1.11
    Activations Density 0.000%

    No Known Activations