© 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. 9172
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
     समाप्त
    0.38
    ;
    0.38
    flu
    0.38
     swimmer
    0.37
     වැ
    0.37
     വ്യാപ
    0.37
     tiet
    0.36
     nyingi
    0.36
    変わり
    0.36
     কমিশনার
    0.35
    POSITIVE LOGITS
    на
    0.43
    сона
    0.40
     expectation
    0.38
    山田
    0.36
    𝘢
    0.35
    ultan
    0.35
    6
    0.35
     contoh
    0.35
    Ellis
    0.35
     samh
    0.35
    Activations Density 0.008%

    No Known Activations