INDEX

Explanations

words used in official reports or analytical contexts, often involving legal, technical, or factual details.

oai_token-act-pair · gemini-2.0-flash

in terms of

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ftagPool

-0.69

 الرياضيه

-0.69

webElementGuid

-0.66

aarrggbb

-0.63

Rptr

-0.63

twimg

-0.62

 Fifty

-0.56

modelBuilder

-0.56

#+#

-0.56

 ModelRenderer

-0.53

POSITIVE LOGITS

on

0.68

 Infórmanos

0.56

 theorems

0.53

 dessus

0.52

 thereon

0.51

Referanser

0.50

सन्दर्भ

0.50

 itſelf

0.48

 myſelf

0.48

gulation

0.48

Activations Density 28.985%

words used in official reports or analytical contexts, often involving legal, technical, or factual details.

in terms of

No Comments

No Known Activations