© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168560
    Prev
    Next
    INDEX
    Explanations

    punctuation and spacing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    {{\
    0.43
    <s>
    0.40
     $\
    0.39
    .${
    0.38
    <sub>
    0.38
    }${
    0.37
    KHTML
    0.37
    )"
    0.37
     ||
    0.36
    sit
    0.36
    POSITIVE LOGITS
    ​
    2.47
    ​,
    2.22
    ​)
    2.05
    ​.
    2.02
    .​
    1.93
    ,​
    1.91
     ​
    1.84
    ​​
    1.60
    .​​
    1.60
    、​
    1.57
    Activations Density 0.000%

    No Known Activations