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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 13473
    Prev
    Next
    INDEX
    Explanations

    negations ("not", "haven't", "can't") and words indicating uncertainty or lack of knowledge.

    oai_token-act-pair · gemini-2.0-flash

    Unfavorable situations

    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
    <bos>
    -0.48
    ple
    -0.47
     properly
    -0.47
    ellement
    -0.46
    mergeFrom
    -0.45
     past
    -0.44
    TestingModule
    -0.44
     Clough
    -0.44
     prism
    -0.43
    stanbul
    -0.43
    POSITIVE LOGITS
     @"/
    0.65
    viewDidLoad
    0.63
    érables
    0.61
    bibfield
    0.59
    Viitteet
    0.56
    GOTREF
    0.56
    WebMethod
    0.56
     culturelles
    0.56
     seduta
    0.56
    didReceive
    0.56
    Activations Density 0.813%

    No Known Activations