INDEX

Explanations

things that can be compiled or source code segments

oai_token-act-pair · gemini-2.0-flash

computer code

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.41

bag

-0.39

poli

-0.38

pas

-0.38

by

-0.38

ka

-0.38

tv

-0.37

kan

-0.37

im

-0.36

http

-0.36

POSITIVE LOGITS

RegressionTest

0.83

 Vikipedi

0.80

rawDesc

0.77

quations

0.72

kloped

0.71

/**

0.70

WebElementEntity

0.69

estinal

0.69

存于互联网档案馆

0.68

Manbalar

0.68

Activations Density 3.457%

things that can be compiled or source code segments

computer code

No Comments

No Known Activations