© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248680
    Prev
    Next
    INDEX
    Explanations

    JSON addresses identifiers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     &:
    0.44
    ?:
    0.43
    .:
    0.38
    퀘
    0.37
    ego
    0.37
    ':'
    0.37
    মুখী
    0.37
    ?;
    0.36
    sé
    0.36
    ]:
    0.35
    POSITIVE LOGITS
    われます
    0.44
    ounty
    0.44
    inement
    0.36
    eine
    0.36
    UpperCase
    0.35
    ರಣ
    0.35
     সামগ্র
    0.34
    cati
    0.34
     besar
    0.34
     జీ
    0.34
    Activations Density 0.001%

    No Known Activations