© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12922
    Prev
    Next
    INDEX
    Explanations

    words about failures, setbacks and problems along with pronouns referring to people.

    oai_token-act-pair · gemini-2.0-flash

    Code identifiers

    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
     failure
    -1.40
     failing
    -1.38
    failure
    -1.32
     Failing
    -1.31
     Failure
    -1.28
     fail
    -1.26
    failing
    -1.26
    Failure
    -1.22
    Failing
    -1.21
     FAILURE
    -1.17
    POSITIVE LOGITS
    WebVitals
    0.60
    LabelTagHelper
    0.49
    upi
    0.47
     TabLayout
    0.47
    seca
    0.44
    orov
    0.44
    Referencer
    0.44
    сква
    0.44
    MockMvc
    0.44
    TagHelper
    0.43
    Activations Density 6.262%

    No Known Activations