© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202066
    Prev
    Next
    INDEX
    Explanations

    Japanese culture and travel

    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_6_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
    ও
    0.98
     depressing
    0.96
    ю
    0.96
    ру
    0.96
    야
    0.95
    ер
    0.92
     wire
    0.91
     courtroom
    0.90
    вання
    0.89
    ное
    0.88
    POSITIVE LOGITS
    ll
    1.28
    ن
    1.22
    im
    1.17
    ni
    1.11
    Eine
    1.09
    }
    1.09
    ns
    1.05
    this
    1.04
    ik
    1.02
    Add
    1.02
    Activations Density 0.000%

    No Known Activations