© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43364
    Prev
    Next
    INDEX
    Explanations

    age of information

    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_13_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
     ieder
    0.50
     Puritan
    0.46
     potete
    0.44
     பெரும்
    0.42
    盽
    0.42
     plaatsen
    0.42
     Presidents
    0.41
     Myrtle
    0.41
     gehad
    0.41
     kanye
    0.41
    POSITIVE LOGITS
    orget
    0.47
    d
    0.46
    för
    0.44
    ם
    0.44
    <%
    0.44
    ేక
    0.44
    高級
    0.43
     havoc
    0.43
    GRADE
    0.42
    ktu
    0.42
    Activations Density 0.000%

    No Known Activations