INDEX

Explanations

conjunctions and pronouns, but it seems to be highly sensitive to the exact case, potentially identifying sentence structure

oai_token-act-pair · gemini-2.0-flash

German and math texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

-0.62

انيف

-0.54

}")]

-0.54

=?";

-0.54

updateOne

-0.54

stdafx

-0.54

NameInMap

-0.51

ものです

-0.48

one

-0.48

还不是

-0.48

POSITIVE LOGITS

脚注の使い方

0.75

ArgsConstructor

0.72

 /\.(

0.66

SequentialGroup

0.63

/\.

0.62

ChromeDriver

0.61

DebuggerStep

0.59

 FileReader

0.58

новниш

0.57

PropertyChanging

0.56

Activations Density 1.594%

conjunctions and pronouns, but it seems to be highly sensitive to the exact case, potentially identifying sentence structure

German and math texts

No Comments

No Known Activations