© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13867
    Prev
    Next
    INDEX
    Explanations

    question phrases asking if anyone has seen something before or knows something

    oai_token-act-pair · gemini-2.0-flash

    anyone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     open
    -0.47
     Open
    -0.47
     собой
    -0.45
     gratuits
    -0.44
    uro
    -0.43
    v
    -0.43
    open
    -0.42
    apunov
    -0.41
     possibles
    -0.41
    Open
    -0.41
    POSITIVE LOGITS
     defStyleAttr
    0.79
    帖最后由
    0.78
    RegressionTest
    0.77
    tagHelperRunner
    0.77
    KURZBESCHREIBUNG
    0.73
    RetentionPolicy
    0.72
    yntaxException
    0.72
     CreateTagHelper
    0.72
    NOPQRST
    0.71
    jsxFileName
    0.68
    Activations Density 0.183%

    No Known Activations