© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197607
    Prev
    Next
    INDEX
    Explanations

    units of length (cm, inches)

    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_15_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
    <0xB5>
    0.40
     MIDDLE
    0.35
    िन
    0.35
     psicol
    0.35
     universo
    0.34
     “‘
    0.34
    َّ
    0.33
    mixin
    0.33
     CONCLUSION
    0.33
    <0xB4>
    0.32
    POSITIVE LOGITS
     бир
    0.39
     знания
    0.37
    icas
    0.37
    бир
    0.36
     после
    0.36
     Bee
    0.36
     వచ్చిన
    0.36
     Wic
    0.35
    Bee
    0.35
     shears
    0.35
    Activations Density 0.002%

    No Known Activations