INDEX

Explanations

words related to geography and outdoor locations

oai_token-act-pair · gemini-2.0-flash

Landforms

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

脚注の使い方

-0.81

 SwitchCompat

-0.71

Viitteet

-0.67

 HasFactory

-0.66

 kasarigan

-0.65

PullParser

-0.63

 typelib

-0.61

 OFDb

-0.61

 contextLoads

-0.61

Espèce

-0.61

POSITIVE LOGITS

bed

0.67

 road

0.63

bed

0.62

cide

0.60

 Road

0.59

Bed

0.54

Rd

0.52

ag

0.52

road

0.52

wall

0.51

Activations Density 6.139%

words related to geography and outdoor locations

Landforms

No Comments

No Known Activations