© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13066
    Prev
    Next
    INDEX
    Explanations

    code snippets with import and tags

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    LookAnd
    -0.81
    IntoConstraints
    -0.71
    +:+
    -0.71
     >=",
    -0.68
    ISupport
    -0.67
    StoryboardSegue
    -0.66
    IsContent
    -0.64
     CanadaChoose
    -0.63
    ValueGeneration
    -0.60
     initComponents
    -0.58
    POSITIVE LOGITS
    ERIA
    0.50
    CLING
    0.48
     ou
    0.48
    uters
    0.47
    telser
    0.47
    gway
    0.47
    ATIVES
    0.47
    يديا
    0.46
     РС
    0.45
    dotta
    0.45
    Activations Density 5.695%

    No Known Activations