© 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. 80066
    Prev
    Next
    INDEX
    Explanations

    nostalgia

    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
     to
    3.20
    to
    2.58
    та
    1.90
    то
    1.57
    1
    1.48
    会
    1.47
    3
    1.45
    তা
    1.34
    都
    1.34
    将
    1.31
    POSITIVE LOGITS
     It
    1.80
     it
    1.48
    It
    1.41
    I
    1.30
    a
    1.30
    اک
    1.23
    E
    1.23
    T
    1.21
    uted
    1.17
    お待ち
    1.14
    Activations Density 0.000%

    No Known Activations