INDEX

Explanations

mentions of geographical places and their involvement in various events or studies.

oai_token-act-pair · gemini-2.0-flash

in

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

 vaikka

-0.52

 questão

-0.51

antaranya

-0.49

 Réponses

-0.48

hésite

-0.47

ņa

-0.47

 antaranya

-0.44

__()

-0.43

XmlType

-0.43

setAccessible

-0.43

POSITIVE LOGITS

 utafitiHapana

0.61

 Reverso

0.60

tagHelperRunner

0.59

atimes

0.56

ttk

0.56

ClCompile

0.56

دانشنامهٔ

0.54

Aholisi

0.53

ods

0.53

ไว

0.52

Activations Density 1.451%

mentions of geographical places and their involvement in various events or studies.

in

No Comments

No Known Activations