INDEX

Explanations

place names associated with directions or locations

oai_token-act-pair · gemini-2.0-flash

into

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

Diweddarwch

-0.53

DockStyle

-0.51

Архівовано

-0.51

Statistiche

-0.51

్వ

-0.50

 arşivlendi

-0.50

__*/

-0.48

 Pert

-0.48

-0.47

κτηρισ

-0.46

POSITIVE LOGITS

 виправивши

0.64

 ExecuteAsync

0.60

PMailer

0.59

 ElementRef

0.59

Gön

0.57

 eventdata

0.56

Ƚ

0.55

bukkit

0.53

ServletRequest

0.52

(&:

0.51

Activations Density 0.834%

place names associated with directions or locations

into

No Comments

No Known Activations