INDEX

Explanations

words that are related to situations, states and formal procedures

oai_token-act-pair · gemini-2.0-flash

on

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 незавершена

-0.93

AndEndTag

-0.85

IntoConstraints

-0.85

AnchorStyles

-0.83

StoryboardSegue

-0.82

BeginContext

-0.80

IsContent

-0.73

DockStyle

-0.72

Hentet

-0.71

bewerken

-0.71

POSITIVE LOGITS

on

2.28

On

1.33

On

1.25

 на

1.16

 على

1.07

ON

1.07

 pada

1.05

auf

1.05

บน

1.04

 trên

0.98

Activations Density 3.745%

words that are related to situations, states and formal procedures

on

No Comments

No Known Activations