© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110591
    Prev
    Next
    INDEX
    Explanations

    Finnish words like `pata`, `Suomi`, `rajapalvelu`

    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_2_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
    ن
    1.62
    ку
    1.42
    م
    1.42
    n
    1.40
    न
    1.39
    al
    1.36
    ке
    1.36
    il
    1.30
    ע
    1.30
    น
    1.23
    POSITIVE LOGITS
    ]
    1.25
    1.20
    }
    1.11
    .
    1.09
    )
    1.01
    \
    1.00
     malicious
    0.97
    .`
    0.93
    \}
    0.90
     сеть
    0.89
    Activations Density 0.001%

    No Known Activations