© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225135
    Prev
    Next
    INDEX
    Explanations

    the story behind

    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_10_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
    Apr
    0.57
    Dn
    0.57
    Pooled
    0.53
    Pooling
    0.49
    Datei
    0.49
     Itália
    0.49
    Organizer
    0.48
    侬
    0.48
    erjee
    0.48
     wirken
    0.48
    POSITIVE LOGITS
     to
    0.49
    _
    0.47
     පිට
    0.46
     Big
    0.46
     le
    0.45
     M
    0.44
     entre
    0.44
    ral
    0.44
    entre
    0.44
     affront
    0.44
    Activations Density 0.000%

    No Known Activations