INDEX

Explanations

sentences advising the reader to think about or examine something

oai_token-act-pair · gemini-2.0-flash

consider

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CloseOperation

-0.89

 ModelExpression

-0.78

 CreateTagHelper

-0.77

sidemargin

-0.76

Portale

-0.72

INSEE

-0.72

 <>",

-0.71

Portály

-0.71

 AssemblyVersion

-0.71

Personendaten

-0.69

POSITIVE LOGITS

 that

0.60

the

0.52

 myself

0.47

top

0.46

 Clark

0.43

 ovan

0.42

 dors

0.42

Clark

0.42

 đối

0.41

all

0.40

Activations Density 11.528%

sentences advising the reader to think about or examine something

consider

No Comments

No Known Activations