© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13488
    Prev
    Next
    INDEX
    Explanations

    rooms and passages

    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_13_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
    ின்ற
    0.47
    Males
    0.40
    aufen
    0.40
    Factors
    0.39
    Además
    0.39
    槃
    0.39
    fila
    0.38
    YLE
    0.38
    tenths
    0.38
    Pup
    0.38
    POSITIVE LOGITS
     l
    0.47
     with
    0.47
    an
    0.46
     appr
    0.46
     n
    0.44
     from
    0.44
     r
    0.43
    ie
    0.42
    r
    0.42
     article
    0.42
    Activations Density 0.030%

    No Known Activations