© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1288
    Prev
    Next
    INDEX
    Explanations

    text from ads that try to sell you something.

    oai_token-act-pair · gemini-2.0-flash

    Random code and text

    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
    MENAFN
    -0.79
    Aholisi
    -0.59
    tvguidetime
    -0.56
    ørs
    -0.54
    saraba
    -0.54
    WithIOException
    -0.54
    oa̍t
    -0.53
    ReusableCell
    -0.52
     pinulongan
    -0.51
     Meksiku
    -0.51
    POSITIVE LOGITS
     ***!
    0.54
     Valera
    0.51
     <=",
    0.50
    endesk
    0.48
     ExecuteAsync
    0.47
    udas
    0.47
    setVerticalGroup
    0.46
    uni
    0.46
    ]-->
    0.45
    mos
    0.45
    Activations Density 2.108%

    No Known Activations