© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17919
    Prev
    Next
    INDEX
    Explanations

    models and systems

    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_34_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
    を目指
    0.36
     fanbase
    0.36
     devastation
    0.35
    ReadToEnd
    0.35
     assimilation
    0.35
    ancipation
    0.35
     이용하여
    0.35
    ዥ
    0.35
     kajian
    0.34
     dissemination
    0.34
    POSITIVE LOGITS
     subject
    0.46
     subiect
    0.44
     grazed
    0.42
     dogged
    0.41
     constructed
    0.41
     manipulated
    0.41
     tattooed
    0.41
     enrolled
    0.40
     nurs
    0.40
     treated
    0.40
    Activations Density 0.494%

    No Known Activations