INDEX

Explanations

the word "clean" and related terms, such as names of cleaning companies

oai_token-act-pair · gemini-2.0-flash

clean

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ViewImports

-0.85

Efq

-0.84

 bezeichneter

-0.83

 raiſ

-0.77

AndEndTag

-0.75

 Theſe

-0.73

//});

-0.71

})`

-0.71

IsContent

-0.71

 doubtnut

-0.71

POSITIVE LOGITS

per

0.47

ab

0.44

sk

0.40

:+:

0.40

out

0.39

OR

0.39

upyter

0.38

opsida

0.38

InSection

0.37

Activations Density 5.188%

the word "clean" and related terms, such as names of cleaning companies

clean

No Comments

No Known Activations