© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142981
    Prev
    Next
    INDEX
    Explanations

    suburban areas and contexts

    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
    ל
    1.52
    lara
    1.44
    ُ
    1.43
    {
    1.40
    8
    1.38
    ס
    1.38
    2
    1.37
    ]
    1.37
    }
    1.36
    ו
    1.35
    POSITIVE LOGITS
    in
    1.70
    is
    1.64
    ра
    1.45
    to
    1.41
    ות
    1.17
    지
    1.17
    at
    1.16
    as
    1.15
    棪
    1.13
    에
    1.13
    Activations Density 0.000%

    No Known Activations