© 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. 12839
    Prev
    Next
    INDEX
    Explanations

    positive encouragement phrases or sentiments

    oai_token-act-pair · gemini-2.0-flash

    Better

    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
     iD
    -0.50
    saraba
    -0.48
     ihn
    -0.47
     '{@
    -0.45
    ggars
    -0.45
     uintptr
    -0.45
    喆
    -0.44
    mí
    -0.43
     among
    -0.43
    getID
    -0.43
    POSITIVE LOGITS
     ostavi
    0.70
     propOrder
    0.65
    Bakgrunnsstoff
    0.65
     MonoBehaviour
    0.53
     poffe
    0.51
    enderror
    0.51
    BeginContext
    0.51
    parsedMessage
    0.51
    asteroide
    0.48
    లాలు
    0.48
    Activations Density 0.078%

    No Known Activations