© 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. 215159
    Prev
    Next
    INDEX
    Explanations

    mountain ranges

    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
     fus
    0.44
    Kings
    0.42
    쿨
    0.41
    ค
    0.40
    キング
    0.40
    吸収
    0.40
    Platinum
    0.40
    𝗞
    0.39
     Kings
    0.39
     Platinum
    0.38
    POSITIVE LOGITS
    ジー
    0.39
     Glow
    0.38
    ﺢ
    0.38
    ட்டர்
    0.38
     வடி
    0.38
    ãos
    0.37
    łow
    0.37
    edic
    0.37
     GBP
    0.36
     Feel
    0.36
    Activations Density 0.001%

    No Known Activations