© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214398
    Prev
    Next
    INDEX
    Explanations

    event and data points

    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_5_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
    am
    1.55
    is
    1.48
    5
    1.44
    9
    1.41
    :
    1.36
    A
    1.24
    _
    1.21
    ing
    1.20
    and
    1.19
    7
    1.19
    POSITIVE LOGITS
    на
    1.27
    म
    1.22
    О
    1.14
    ne
    1.10
    بد
    1.09
    م
    1.05
    ೂ
    1.05
    مس
    1.03
    กก
    1.02
    भ
    1.02
    Activations Density 0.000%

    No Known Activations