© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242595
    Prev
    Next
    INDEX
    Explanations

    the morning

    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_40_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
    Travel
    0.38
    edì
    0.37
     carnival
    0.35
    여행
    0.34
    신
    0.34
     handshake
    0.33
     traveling
    0.33
    Eli
    0.33
    เดินทาง
    0.33
     TRAVEL
    0.33
    POSITIVE LOGITS
     болу
    0.40
     பாதை
    0.38
     साझे
    0.36
    }$&$-
    0.36
    ເທ
    0.35
     частина
    0.34
     जाये
    0.34
     olmad
    0.34
     だけ
    0.34
    HideFlags
    0.34
    Activations Density 0.004%

    No Known Activations