INDEX

Explanations

code snippets or examples.

oai_token-act-pair · gemini-2.0-flash

Code and API related text

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

]")]

-0.55

ⓧ

-0.44

 Ause

-0.40

)++;

-0.37

PathVariable

-0.36

caloosa

-0.36

PerformLayout

-0.35

.))

-0.35

MessageOf

-0.35

 element

-0.35

POSITIVE LOGITS

addPreferredGap

0.77

 resourceCulture

0.61

 Cæsar

0.57

 popoli

0.56

 Galo

0.56

 nephe

0.56

 vuoto

0.53

Ligações

0.53

 larmes

0.53

 ThemeData

0.52

Activations Density 1.465%

code snippets or examples.

Code and API related text

No Comments

No Known Activations