INDEX

Explanations

mentions of literal or metaphorical fires

oai_token-act-pair · gemini-2.0-flash

fire

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

GOTREF

-0.56

 Unterhaltung

-0.55

 fought

-0.54

 Atem

-0.54

 ActivatedRoute

-0.53

put

-0.53

 snippetHide

-0.52

 battled

-0.52

anais

-0.51

 MainAxisSize

-0.51

POSITIVE LOGITS

 fire

1.41

fire

1.22

 FIRE

1.21

Fire

1.20

 Fire

1.17

FIRE

1.10

 fires

0.96

fires

0.93

 firefighters

0.86

 fireplace

0.85

Activations Density 0.645%

mentions of literal or metaphorical fires

fire

No Comments

No Known Activations