© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16184
    Prev
    Next
    INDEX
    Explanations

    a combination of words like "you," "to," "can," "the," and auxiliary verbs, indicating an attempt to identify instructions or suggestions directed at someone.

    oai_token-act-pair · gemini-2.0-flash

    face

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    StoryboardSegue
    -0.83
     Wiktionnaire
    -0.76
    MessageOf
    -0.75
    Personensuche
    -0.71
     saites
    -0.67
    MigrationBuilder
    -0.66
    OGND
    -0.65
    cluye
    -0.61
    protoimpl
    -0.59
    rawDesc
    -0.59
    POSITIVE LOGITS
     face
    3.63
    face
    3.05
    Face
    2.94
     Face
    2.89
     faces
    2.84
     FACE
    2.56
    FACE
    2.31
    faces
    2.28
     Faces
    2.13
    faced
    2.03
    Activations Density 5.562%

    No Known Activations