© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195198
    Prev
    Next
    INDEX
    Explanations

    Dependabot, funding, email, June

    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_27_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
     لاہور
    0.40
     heft
    0.37
     odds
    0.36
     indice
    0.36
     \}$
    0.35
     compet
    0.35
    ForRow
    0.34
     blah
    0.34
     schle
    0.34
     \}
    0.34
    POSITIVE LOGITS
    ACY
    0.39
     தோட்ட
    0.39
     любви
    0.39
     criticise
    0.39
     odkazy
    0.39
    ru
    0.38
     사랑
    0.38
     сказал
    0.38
     আর্কাইভ
    0.38
    भू
    0.37
    Activations Density 0.000%

    No Known Activations