© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158268
    Prev
    Next
    INDEX
    Explanations

    provide reasons

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Samantha
    0.45
    Samantha
    0.45
     SAMP
    0.44
     쉽
    0.43
    osate
    0.42
    াধ্য
    0.41
    Samp
    0.40
     سام
    0.39
    ્યાં
    0.39
     甲
    0.38
    POSITIVE LOGITS
     K
    0.43
    James
    0.41
     Gan
    0.40
     Merr
    0.40
    Gan
    0.39
    jami
    0.39
     सिव
    0.37
     fringilla
    0.37
    Merr
    0.37
     gan
    0.36
    Activations Density 0.010%

    No Known Activations