INDEX

Explanations

hyperlinks, references, and categories related to biographical data

oai_token-act-pair · gemini-2.0-flash

links/references

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Paglinawan

-0.77

Scénario

-0.65

IBAction

-0.65

aarrggbb

-0.60

 ब्रेकडाउन

-0.59

openConnection

-0.57

">+

-0.57

Abitanti

-0.56

---*/

-0.55

Introduced

-0.55

POSITIVE LOGITS

 cherchés

0.52

 ràng

0.47

хьтан

0.41

Personendaten

0.41

 Planet

0.41

ffin

0.41

Planet

0.40

 project

0.40

gerufen

0.40

mployment

0.39

Activations Density 1.122%

hyperlinks, references, and categories related to biographical data

links/references

No Comments

No Known Activations