© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161867
    Prev
    Next
    INDEX
    Explanations

    describing location

    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_2_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
    ط
    1.33
    c
    1.28
    }).
    1.25
    r
    1.25
    (
    1.23
    on
    1.20
    }
    1.19
    sh
    1.17
    v
    1.16
    x
    1.14
    POSITIVE LOGITS
    ং
    1.25
    ită
    1.22
     mismas
    1.20
    ě
    1.17
    I
    1.16
    IAN
    1.14
    ্রম
    1.13
    IKA
    1.13
    ным
    1.12
    ară
    1.11
    Activations Density 0.000%

    No Known Activations