© 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. 42360
    Prev
    Next
    INDEX
    Explanations

    google font family links

    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
     двох
    0.43
    чого
    0.41
    Choisissez
    0.41
     딸
    0.39
    Chois
    0.39
     சர்
    0.38
     прийма
    0.38
    
    0.38
     แล้ว
    0.36
     Тогда
    0.35
    POSITIVE LOGITS
    rocities
    0.46
     आफ्
    0.44
    apabb
    0.44
    睦
    0.43
    更大的
    0.41
     hina
    0.40
     escritorio
    0.40
     निष्कर्ष
    0.40
    dain
    0.40
     enlarge
    0.39
    Activations Density 0.000%

    No Known Activations