© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161394
    Prev
    Next
    INDEX
    Explanations

    pueda + verb infinitive

    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_2_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
    ння
    1.21
    ते
    1.11
    กัน
    1.06
    2
    1.06
    ется
    1.04
    AK
    1.02
     pubblic
    1.02
    ING
    1.02
    \
    1.02
     gått
    1.00
    POSITIVE LOGITS
    x
    1.76
    ون
    1.52
    י
    1.46
    is
    1.38
    ec
    1.36
    isinin
    1.36
    ності
    1.33
    id
    1.32
    ie
    1.23
     keyed
    1.22
    Activations Density 0.001%

    No Known Activations