© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145933
    Prev
    Next
    INDEX
    Explanations

    gifted someone something

    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_0_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
     in
    2.16
    ]
    1.59
     on
    1.41
    も
    1.41
    在
    1.37
    ও
    1.30
    _
    1.26
    >
    1.22
    도
    1.22
     of
    1.16
    POSITIVE LOGITS
    ب
    2.41
    ด
    1.53
    ين
    1.52
    is
    1.48
    ク
    1.44
    يد
    1.41
    ס
    1.40
    ز
    1.34
    ти
    1.33
    ות
    1.32
    Activations Density 0.000%

    No Known Activations