© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107501
    Prev
    Next
    INDEX
    Explanations

    Hungarian words like "milliárd" or "porfészek"

    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_1_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
    to
    1.30
    in
    1.09
    i
    1.06
     from
    1.05
     in
    0.99
    is
    0.98
     for
    0.95
    ine
    0.90
    l
    0.90
    elle
    0.89
    POSITIVE LOGITS
    })$.
    1.13
    이었다
    1.11
    ف
    1.10
    }]$.
    1.07
    }).
    1.06
    {
    1.02
     Elektrokh
    1.02
    },
    1.01
    }=
    1.00
    :
    1.00
    Activations Density 0.000%

    No Known Activations