© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258972
    Prev
    Next
    INDEX
    Explanations

    usually followed by common usage

    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_22_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
     (†
    0.42
     ())
    0.41
     ():
    0.41
     US
    0.40
     PROVIDED
    0.39
    ⽇
    0.38
    aleigh
    0.38
    لم
    0.38
     बताते
    0.38
    연
    0.37
    POSITIVE LOGITS
     ulcers
    0.41
     किसके
    0.40
    ቆዳ
    0.40
    bowl
    0.39
     jabs
    0.39
     lens
    0.38
     Tuberculosis
    0.38
     hapless
    0.38
     cervix
    0.38
     முழுக்க
    0.38
    Activations Density 0.009%

    No Known Activations