© 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. 5672
    Prev
    Next
    INDEX
    Explanations

    words or phrases referring to communication and reaction

    oai_token-act-pair · gemini-2.0-flash

    response

    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
    Rè
    -0.67
    gdx
    -0.65
    BASEPATH
    -0.64
    Coordonnées
    -0.60
     Spisak
    -0.58
    HasAnnotation
    -0.56
    zeichnis
    -0.54
    gameserver
    -0.54
    έα
    -0.53
    #+#
    -0.52
    POSITIVE LOGITS
     to
    0.82
     Pingback
    0.49
     Normdatei
    0.47
    couvrez
    0.46
    importante
    0.46
    depuis
    0.44
     σήμερα
    0.44
     нея
    0.43
     чтобы
    0.43
     abzu
    0.42
    Activations Density 14.569%

    No Known Activations