© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175181
    Prev
    Next
    INDEX
    Explanations

    release and codename

    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_20_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
    行った
    0.25
    ,“
    0.25
    Ꮦ
    0.25
     taxonomy
    0.24
    阠
    0.23
     fascinated
    0.22
    ①
    0.22
     નવી
    0.22
    ➀
    0.21
    溸
    0.21
    POSITIVE LOGITS
    endedores
    0.21
     সাপ্তাহিক
    0.20
     P
    0.20
    خش
    0.19
    qquad
    0.19
    Pixels
    0.19
    LE
    0.19
    Phi
    0.18
    quisa
    0.18
    HASH
    0.18
    Activations Density 0.004%

    No Known Activations