© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141614
    Prev
    Next
    INDEX
    Explanations

    command `tool`

    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_12_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
    calorie
    0.55
    торин
    0.55
    ل
    0.54
    ک
    0.54
    sparse
    0.50
    ])
    0.50
    screening
    0.50
    t
    0.49
    тор
    0.48
    ወሰ
    0.47
    POSITIVE LOGITS
    ÈRE
    0.54
    ÔNG
    0.54
     destinée
    0.52
    ÖR
    0.52
     añ
    0.51
     детьми
    0.51
    året
    0.50
    CM
    0.50
    ONY
    0.50
     erhältlich
    0.50
    Activations Density 0.001%

    No Known Activations