INDEX

Explanations

sql queries

np_max-act-logits · gemini-2.0-flash

source code snippets, especially SQL and PHP

oai_token-act-pair · gemini-2.0-flash

SQL code

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

]}>

-0.47

واس

-0.44

-0.43

mol

-0.42

اده

-0.42

exp

-0.42

createCanvas

-0.41

Exp

-0.41

Geografie

-0.41

boa

-0.41

POSITIVE LOGITS

tagHelperRunner

0.96

AddTagHelper

0.93

DockStyle

0.81

 يتيمه

0.81

 Roskov

0.79

+#+#

0.78

InputBorder

0.78

 مرئيه

0.75



0.72

ValueStyle

0.71

Activations Density 3.438%

sql queries

source code snippets, especially SQL and PHP

SQL code

No Comments

No Known Activations