© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1048
    Prev
    Next
    INDEX
    Explanations

    words or phrases that express being unfinished or incomplete

    oai_token-act-pair · gemini-2.0-flash

    code/technical and unfinished

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     yet
    -3.52
    yet
    -3.23
     Yet
    -3.06
    Yet
    -3.05
     YET
    -2.61
     endnu
    -1.59
     ännu
    -1.52
     Pourtant
    -1.38
     aún
    -1.27
    ppure
    -1.26
    POSITIVE LOGITS
     propOrder
    0.54
    WriteBarrier
    0.54
    abspath
    0.51
    *>(
    0.50
     QName
    0.50
    xtext
    0.50
    ')"
    0.48
    >`
    0.48
    >>()
    0.47
    Literatur
    0.47
    Activations Density 6.392%

    No Known Activations