INDEX

Explanations

different languages

oai_token-act-pair · gemini-2.0-flash

Past tense verbs

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

 would

-0.85

would

-0.81

 will

-0.75

 Would

-0.71

 оригіналу

-0.71

 fhould

-0.71

 WOULD

-0.66

ShouldBe

-0.66

can

-0.65

exitRule

-0.65

POSITIVE LOGITS

was

0.95

did

0.94

 came

0.91

 took

0.90

 went

0.87

 gave

0.84

 began

0.81

 ended

0.79

Did

0.77

did

0.76

Activations Density 0.499%

different languages

Past tense verbs

No Comments

No Known Activations