© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218522
    Prev
    Next
    INDEX
    Explanations

    make sure

    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_31_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
    ണ്യ
    0.41
    द्दी
    0.39
     внима
    0.38
    வேன்
    0.38
     काळजी
    0.38
    の一部
    0.37
     યોગ
    0.35
    𒁉
    0.35
     সংয
    0.35
    POSITIVE LOGITS
    shuffle
    0.44
    fill
    0.37
     compr
    0.37
    фар
    0.36
     حين
    0.36
     Orche
    0.35
    slots
    0.35
    intrusion
    0.35
     minist
    0.35
    leader
    0.34
    Activations Density 0.000%

    No Known Activations