INDEX

Explanations

contexts where something is appropriate or intended for something else

oai_token-act-pair · gemini-2.0-flash

for

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

]")]

-0.84

Kaynakça

-0.82

 مشين

-0.79

setVerticalGroup

-0.77

twimg

-0.76

'{@

-0.71

providedIn

-0.69

انجليز

-0.68

AlterField

-0.67

SharedDtor

-0.67

POSITIVE LOGITS

 passing

0.65

 storing

0.54

 taking

0.54

 younger

0.53

 having

0.52

icale

0.52

 riding

0.50

ListFragment

0.49

 doing

0.48

 living

0.48

Activations Density 2.659%

contexts where something is appropriate or intended for something else

for

No Comments

No Known Activations