© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9701
    Prev
    Next
    INDEX
    Explanations

    fragments of Spanish text

    oai_token-act-pair · gemini-2.0-flash

    the letter 'a' in various contexts

    np_token-act-pair-logits · gpt-4o-mini

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    SurfaceView
    -0.47
    EditorBrowsable
    -0.46
    XmlEnum
    -0.46
     calldata
    -0.44
    alignSelf
    -0.43
    ]")]
    -0.43
    prepareStatement
    -0.42
     jsPsych
    -0.42
     BoxFit
    -0.42
    riture
    -0.41
    POSITIVE LOGITS
    مصادر
    0.67
    RegressionTest
    0.58
    Становништво
    0.55
    HORE
    0.54
    abestanden
    0.54
     createState
    0.53
     makeStyles
    0.53
    ี่ย
    0.53
    ayage
    0.53
    CGRectMake
    0.52
    Activations Density 0.210%

    No Known Activations