© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211017
    Prev
    Next
    INDEX
    Explanations

    calculus chain rule

    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_5_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
    <0x0D>
    1.51
    ie
    1.41
    at
    1.38
    س
    1.34
    s
    1.30
    ra
    1.20
    с
    1.18
    ного
    1.17
    ర్
    1.13
    ig
    1.12
    POSITIVE LOGITS
     οποίο
    1.25
     ו
    1.16
    IS
    1.05
     avaient
    1.05
     kuhusu
    1.05
     działal
    1.03
     ιστο
    1.02
     którym
    1.00
     ainult
    0.98
    多い
    0.97
    Activations Density 0.000%

    No Known Activations