INDEX

Explanations

labels or headings denoting sources, categories, or copyright notices.

oai_token-act-pair · gemini-2.0-flash

website source code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

RunAsync

-0.74

Hozzáférés

-0.73

__;

-0.72

سطس

-0.71

FieldNumber

-0.71

RTLI

-0.70

"]();

-0.70

 protoimpl

-0.69

WEBPACK

-0.69

 considérons

-0.69

POSITIVE LOGITS

<bos>

1.05

expandindo

0.49

 autorytatywna

0.48

its

0.45

 scuro

0.43

 nargin

0.42

 condamné

0.41

łości

0.40

<eos>

0.40

Δείτε

0.40

Activations Density 0.908%

labels or headings denoting sources, categories, or copyright notices.

website source code

No Comments

No Known Activations