INDEX

Explanations

-

np_max-act-logits · gemini-2.0-flash

image filenames in a particular format

oai_token-act-pair · gemini-2.0-flash

image captions and references to figures

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ródło

-0.53

Билгалдахарш

-0.48

неопр

-0.48

 trữ

-0.47

 giá

-0.46

PrototypeOf

-0.45

ällor

-0.44

Ārējās

-0.44

 发表于

-0.44

FieldValue

-0.44

POSITIVE LOGITS

 nahilalakip

0.75

 Ababa

0.63

PreferredItem

0.63

writeFieldEnd

0.60



0.57

تقاوى

0.57

GEBURTSDATUM

0.56

 Mathilde

0.55

 Infórmanos

0.55

///</

0.55

Activations Density 1.456%

-

image filenames in a particular format

image captions and references to figures

No Comments

No Known Activations