© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35486
    Prev
    Next
    INDEX
    Explanations

    mutually agreed upon

    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_3_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
    อาด
    0.64
    போது
    0.63
    er
    0.63
    lly
    0.63
    ه
    0.63
     Puppy
    0.62
    lty
    0.62
    饰演
    0.61
     Vail
    0.61
    a
    0.61
    POSITIVE LOGITS
    ]
    0.69
    리
    0.65
    ED
    0.63
    ction
    0.62
    /******/
    0.61
    }
    0.59
    )
    0.58
    RI
    0.57
    ats
    0.57
    ällen
    0.56
    Activations Density 0.004%

    No Known Activations