© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192708
    Prev
    Next
    INDEX
    Explanations

    end effects or end mill

    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_4_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
    想法
    0.77
    며
    0.75
     đạt
    0.74
    える
    0.74
     рамках
    0.71
     підпри
    0.71
    መሳሳይ
    0.70
    맟
    0.69
    ーム
    0.69
    maligngroup
    0.69
    POSITIVE LOGITS
     n
    1.26
    ר
    1.25
     s
    1.11
     p
    1.10
     v
    1.08
     m
    1.05
     is
    1.05
     I
    1.04
     b
    0.99
     l
    0.96
    Activations Density 0.000%

    No Known Activations