© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5527
    Prev
    Next
    INDEX
    Explanations

    descriptions of the features of a house

    oai_token-act-pair · gemini-2.0-flash

    Bathrooms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.86
    AddTagHelper
    -0.82
     CanadaChoose
    -0.76
    StoryboardSegue
    -0.71
    جوايز
    -0.70
     NSCoder
    -0.68
     passés
    -0.67
    ranean
    -0.66
     صوتيه
    -0.65
     ControllerBase
    -0.65
    POSITIVE LOGITS
     basa
    0.44
     power
    0.44
    am
    0.42
    теристика
    0.41
     uta
    0.39
    CharField
    0.39
    power
    0.39
     Par
    0.38
     hoàn
    0.38
    log
    0.37
    Activations Density 0.584%

    No Known Activations