© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14876
    Prev
    Next
    INDEX
    Explanations

    words ending in "ed", especially related to actions (often verbs in past tense or participles) but also some nouns.

    oai_token-act-pair · gemini-2.0-flash

    ped

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     "..\..\
    -0.93
    avax
    -0.85
    StoryboardSegue
    -0.77
    rungsseite
    -0.76
    Personensuche
    -0.75
    teps
    -0.74
     "..\..\..\
    -0.74
     firebaseConfig
    -0.74
    lgari
    -0.73
     dataSnapshot
    -0.73
    POSITIVE LOGITS
    [toxicity=0]
    0.59
    ley
    0.54
    lee
    0.50
    ruf
    0.49
    ing
    0.49
    bant
    0.48
    ant
    0.47
    ash
    0.46
     away
    0.45
    end
    0.45
    Activations Density 1.558%

    No Known Activations