© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11837
    Prev
    Next
    INDEX
    Explanations

    phrases that describe secrets, keeping things quiet, or holding something back

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or programming terms

    np_token-act-pair-logits · gpt-4o-mini

    keeping things quiet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ValueStyle
    -0.46
    FormBuilder
    -0.43
    SuccessListener
    -0.43
    IUrlHelper
    -0.43
     blevet
    -0.42
    ficamente
    -0.40
     onItemClick
    -0.39
     crede
    -0.39
    InjectMocks
    -0.38
    every
    -0.38
    POSITIVE LOGITS
     Audiodateien
    0.70
    useNewUrlParser
    0.64
    ariConfig
    0.64
    OGND
    0.63
    ecraft
    0.62
    SError
    0.62
    strophic
    0.61
    stag
    0.61
    tvguidetime
    0.60
    {#
    0.60
    Activations Density 1.788%

    No Known Activations