© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4316
    Prev
    Next
    INDEX
    Explanations

    story and plot descriptions

    oai_token-act-pair · gemini-2.0-flash

    Following a story

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    IntoConstraints
    -0.72
     resourceCulture
    -0.62
    verständlich
    -0.55
     eyel
    -0.53
     >=",
    -0.53
    τως
    -0.53
     Normdatei
    -0.52
    NameInMap
    -0.52
     reç
    -0.52
    SizeF
    -0.52
    POSITIVE LOGITS
    Pri
    0.46
     Проци
    0.42
     pri
    0.40
    ManagedBean
    0.40
     Pri
    0.39
    Embeddable
    0.39
    jmp
    0.39
     case
    0.39
    pri
    0.38
    誇
    0.38
    Activations Density 2.699%

    No Known Activations