INDEX

Explanations

words used in scientific studies and descriptions of insects

oai_token-act-pair · gemini-2.0-flash

statistics and rates

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 continúas

-0.65

 becauſe

-0.60

 ComVisible

-0.60

 hâte

-0.57

 myſelf

-0.57

 themſelves

-0.56

 himſelf

-0.55

 whoſe

-0.54

 ſtill

-0.54

 uſed

-0.53

POSITIVE LOGITS

TintMode

0.77

PreferredItem

0.73

 capacity

0.68

capacity

0.66

Jereo

0.63

 Index

0.62

LLocation

0.61

исленность

0.61

 index

0.60

 span

0.58

Activations Density 1.659%

words used in scientific studies and descriptions of insects

statistics and rates

No Comments

No Known Activations