© 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. 177783
    Prev
    Next
    INDEX
    Explanations

    code and commands

    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
     రి
    0.46
     ರಿ
    0.45
     Ри
    0.44
     RE
    0.42
     ರೋ
    0.41
     Ρ
    0.41
    রি
    0.40
     রিপ
    0.40
     ਰ
    0.40
    ΡΙ
    0.40
    POSITIVE LOGITS
    Ub
    0.41
    move
    0.38
    fine
    0.38
    PARAMS
    0.37
    turned
    0.36
    annotate
    0.36
    Pretty
    0.35
    clear
    0.35
    taught
    0.35
    APC
    0.34
    Activations Density 0.010%

    No Known Activations