INDEX

Explanations

file operations like opening, reading, and copying in code

oai_token-act-pair · gemini-2.0-flash

file operations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

writeFieldEnd

-0.74

StoryboardSegue

-0.71

GEBURTSDATUM

-0.69

BeginContext

-0.68

ReusableCell

-0.67

 kaarangay

-0.67

IntoConstraints

-0.66

Geplaatst

-0.63

ToMove

-0.62

OGND

-0.62

POSITIVE LOGITS

 mode

0.69

mode

0.59

 extra

0.57

MODE

0.52

Mode

0.52

ndia

0.52

 comuniques

0.51

 MODE

0.50

 Mode

0.50

تر

0.47

Activations Density 0.433%

file operations like opening, reading, and copying in code

file operations

No Comments

No Known Activations