© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2597
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words and phrases related to human experience, therapy, scientific studies, and personal journeys, showing a broad but potentially unfocused understanding of these topics.

    oai_token-act-pair · gemini-2.0-flash

    Past tense/participle verbs

    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
    #+#
    -0.40
    sample
    -0.39
    Initial
    -0.39
    そうそう
    -0.38
    Right
    -0.36
    <
    -0.36
    ね
    -0.35
    sk
    -0.35
    кры
    -0.35
     život
    -0.34
    POSITIVE LOGITS
    awtextra
    0.94
    AndEndTag
    0.88
    tagHelperRunner
    0.86
    InSection
    0.85
    enumii
    0.85
    rungsseite
    0.83
     CreateTagHelper
    0.83
     صوتيه
    0.82
    脚注の使い方
    0.81
    +:+
    0.81
    Activations Density 7.363%

    No Known Activations