© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138569
    Prev
    Next
    INDEX
    Explanations

    price ranges

    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_37_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
    appelle
    0.40
     AdapterView
    0.38
    ሎ
    0.37
     lessons
    0.36
     examining
    0.36
     पॉप
    0.36
     Sanford
    0.36
     filling
    0.36
    poons
    0.36
     Vf
    0.36
    POSITIVE LOGITS
    alcohol
    0.46
     schal
    0.45
     acreditar
    0.43
    অল
    0.41
    果
    0.41
    Alcohol
    0.40
    Qua
    0.40
    synchron
    0.39
     superconductor
    0.39
     alcohol
    0.38
    Activations Density 0.002%

    No Known Activations