© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9525
    Prev
    Next
    INDEX
    Explanations

    personal opinions and reflections on current and future states.

    oai_token-act-pair · gemini-2.0-flash

    remains

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     صوتيه
    -0.81
    RenderAtEndOf
    -0.76
    таратура
    -0.75
    LookAnd
    -0.66
    WriteBarrier
    -0.65
    MessageTagHelper
    -0.64
     nahilalakip
    -0.64
    ंदीखरीदारी
    -0.63
    enterOuterAlt
    -0.62
    Personendaten
    -0.62
    POSITIVE LOGITS
     remains
    1.39
    remains
    1.08
     remain
    1.05
     Remains
    0.96
     unclear
    0.86
    remain
    0.86
     unknown
    0.84
     remained
    0.81
     остается
    0.79
     depends
    0.76
    Activations Density 1.367%

    No Known Activations